© 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. 99251
    Prev
    Next
    INDEX
    Explanations

    therapeutic drug or treatments

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

    The neuron detects the word "therapeutic" in medical contexts, often relating to drug treatments or medical interventions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ⢊
    -2.72
    皤
    -2.42
     lament
    -2.41
    蜮
    -2.36
    鏷
    -2.28
     The
    -2.28
    翆
    -2.19
     WHEN
    -2.17
     remarkably
    -2.16
    ☆☆☆☆
    -2.16
    POSITIVE LOGITS
    $
    2.59
    2.45
    *
    2.33
     ikke
    2.33
     глазах
    2.31
    ’”
    2.20
     poignant
    2.17
    汾
    2.16
     noteworthy
    2.16
    ...”
    2.13
    Activations Density 0.012%
    No Known Activations