© 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. 59308
    Prev
    Next
    INDEX
    Explanations

    library management

    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
    '
    -2.91
    ↵
    -2.86
    CHREIB
    -2.50
    姽
    -2.42
     Они
    -2.25
     แต่
    -2.25
    fromnode
    -2.19
    ‪.‬‬
    -2.17
    exao
    -2.13
    CHOOL
    -2.11
    POSITIVE LOGITS
    </h3>
    3.42
     {
    3.20
    u
    3.05
    ه
    2.91
    ে
    2.80
    ";
    2.73
    ="
    2.72
    );
    2.66
    ）』
    2.56
    en
    2.47
    Activations Density 0.001%

    No Known Activations