© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60077
    Prev
    Next
    INDEX
    Explanations

    assisted death

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

    scientific and medical terminology, particularly in academic or formal text.

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

    The neuron is specifically triggered by occurrences of the word “type.”

    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
     yoksa
    -1.48
    !».
    -1.40
     olsa
    -1.40
    !).
    -1.38
    »:
    -1.33
    却被
    -1.32
     veya
    -1.29
     voyez
    -1.27
     meneg
    -1.25
    竟然是
    -1.25
    POSITIVE LOGITS
     τελευτα
    1.58
     Verbesserung
    1.34
     täglichen
    1.33
     also
    1.32
    üğü
    1.28
     üblichen
    1.28
     Ausdrücke
    1.27
     見え
    1.27
     übrigen
    1.27
     материала
    1.26
    Activations Density 0.000%

    No Known Activations