© 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. 3002
    Prev
    Next
    INDEX
    Explanations

    assault 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
     recommendation
    -0.79
     tracks
    -0.75
    吵架
    -0.73
     practical
    -0.70
    回忆
    -0.70
    uelta
    -0.69
    RESULT
    -0.68
     factor
    -0.68
     access
    -0.68
     priority
    -0.67
    POSITIVE LOGITS
    ktan
    0.85
    óricos
    0.84
     Levante
    0.77
    uelles
    0.77
    tà
    0.77
    Ğ
    0.76
    inium
    0.76
    ciclopedia
    0.74
     eren
    0.74
    онов
    0.73
    Activations Density 0.020%

    No Known Activations