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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110969
    Prev
    Next
    INDEX
    Explanations

    rape and sexual assault

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    涮
    -0.81
     slaughtered
    -0.79
     Killing
    -0.75
    atsun
    -0.74
    Hasan
    -0.73
     chromium
    -0.73
    ванович
    -0.73
    popd
    -0.72
    poietic
    -0.71
    ⠴
    -0.71
    POSITIVE LOGITS
     rape
    3.80
     raped
    2.98
     Rape
    2.86
    rape
    2.75
    Rape
    2.66
     raping
    2.47
     sexual
    2.20
     rapist
    2.02
    Sexual
    1.96
     Sexual
    1.93
    Activations Density 0.062%

    No Known Activations