© 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. 34-GEMMASCOPE-RES-131K
    7. 106654
    Prev
    Next
    INDEX
    Explanations

    sexual assault and offenses

    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
    lites
    -0.91
    borns
    -0.79
    部分を
    -0.73
    玩笑
    -0.72
     esternos
    -0.72
    Interpret
    -0.72
    lente
    -0.72
    aughter
    -0.72
     Alegre
    -0.70
     angka
    -0.69
    POSITIVE LOGITS
     thầy
    0.92
     loco
    0.91
    Child
    0.84
     Child
    0.82
     σο
    0.81
    最近
    0.80
     Coaching
    0.80
     lepton
    0.79
     шоколад
    0.76
    сту
    0.75
    Activations Density 0.025%

    No Known Activations