© 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. 67272
    Prev
    Next
    INDEX
    Explanations

    violent actions

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

    The neuron activates strongly on words naming violent criminal actions (e.g. killed, shot, stabbed, raped).

    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
     from
    -1.47
     that
    -1.27
    Ngo
    -1.21
    最后由
    -1.19
     adecuados
    -1.19
     all
    -1.17
     Wartawan
    -1.17
    栢
    -1.13
    INGE
    -1.12
    Мон
    -1.10
    POSITIVE LOGITS
    訁
    1.17
    เล็ก
    1.16
     equivalente
    1.10
    ֥
    1.09
     evitando
    1.07
     esté
    1.06
    tabilité
    1.05
     малень
    1.05
     Gerais
    1.05
    licité
    1.04
    Activations Density 0.065%

    No Known Activations