© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38600
    Prev
    Next
    INDEX
    Explanations

    brutal or savage violence

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

    This neuron detects language describing violence or brutality (e.g., “brutal,” “mutilated,” “violent,” “graphic”).

    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
     predomin
    -1.77
    </h3>
    -1.73
    (
    -1.61
    e
    -1.55
    '}}>
    -1.55
    ?
    -1.53
    . 
    -1.52
     perpet
    -1.49
    ´
    -1.48
    al
    -1.45
    POSITIVE LOGITS
    สอง
    1.95
     dwie
    1.72
     estos
    1.70
    行きます
    1.70
     двух
    1.66
    あっという間に
    1.59
     две
    1.58
    もありました
    1.56
    idlertid
    1.56
    もあった
    1.53
    Activations Density 0.029%

    No Known Activations