© 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. 10-GEMMASCOPE-RES-131K
    7. 39390
    Prev
    Next
    INDEX
    Explanations

    criminal activity and charges

    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_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
    \
    -2.64
    ﺅ
    -1.85
    '
    -1.81
    後記
    -1.77
     armes
    -1.76
    买的
    -1.73
    Tienda
    -1.70
    ।
    -1.66
     \"
    -1.63
     ſtand
    -1.60
    POSITIVE LOGITS
    ↵
    2.14
     to
    2.05
    也
    1.87
     Mientras
    1.69
     Debido
    1.62
     sınır
    1.61
    ți
    1.61
    1
    1.57
    FTP
    1.56
     start
    1.55
    Activations Density 0.011%

    No Known Activations