© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100519
    Prev
    Next
    INDEX
    Explanations

    untreated patients or conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    The word "untreated" in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron identifies the word "untreated" in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron identifies the word "untreated" in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects the word "untreated" in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "untreated" in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The word "untreated" in medical or scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specifically detects occurrences of the word “untreated.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .”
    -3.02
    筇
    -2.61
    
    -2.41
    ’
    -2.39
    ágenes
    -2.38
    ጪ
    -2.36
     ähnliche
    -2.34
    ",
    -2.33
    ೣ
    -2.33
    u
    -2.28
    POSITIVE LOGITS
    踅
    3.02
    ࿚
    2.78
     intérieure
    2.72
     extérieure
    2.72
    誊
    2.63
     féminine
    2.45
    独特
    2.41
     It
    2.39
    ᠁
    2.36
     للاس
    2.25
    Activations Density 0.006%

    No Known Activations