© 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. 84552
    Prev
    Next
    INDEX
    Explanations

    filter lists

    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
    Contenu
    -1.95
    s
    -1.94
    场面
    -1.88
    ↵↵
    -1.80
    Ingrédients
    -1.79
    鵟
    -1.78
     plupart
    -1.73
    In
    -1.70
    辈子
    -1.63
     Redewendung
    -1.58
    POSITIVE LOGITS
     $
    2.05
     participaron
    1.98
     この
    1.92
    鴣
    1.90
    に
    1.88
    𐑂
    1.87
    ার
    1.85
    ).
    1.85
    érape
    1.83
     该
    1.79
    Activations Density 0.042%

    No Known Activations