© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86091
    Prev
    Next
    INDEX
    Explanations

    names like Cooke, Clarke, Moore, Brent, Freeman, Caldwell, Taylor

    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
     consejo
    -1.66
     modifies
    -1.66
     dictates
    -1.63
    抵达
    -1.60
    你别
    -1.55
    怎么能
    -1.55
    刖
    -1.55
     designates
    -1.54
     poquito
    -1.54
     ส์
    -1.53
    POSITIVE LOGITS
    </h4>
    1.83
    $,
    1.77
    </sup>
    1.77
     Saltar
    1.72
    ']);
    1.60
    ！！！”
    1.59
    ！"
    1.52
    parsedMessage
    1.45
    /}{
    1.43
    ”、“
    1.41
    Activations Density 0.109%

    No Known Activations