© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85624
    Prev
    Next
    INDEX
    Explanations

    the most important

    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
    </i>
    -2.33
    ";
    
    -2.30
    e
    -2.03
    </th>
    -1.91
    ",
    
    -1.78
     Перейти
    -1.70
    1
    -1.66
     and
    -1.63
    ,}
    -1.63
    ';
    
    -1.60
    POSITIVE LOGITS
     of
    2.20
    ↵
    1.95
     \
    1.80
    轳
    1.75
    empuan
    1.59
    ANIE
    1.59
    ADING
    1.58
    一个月
    1.55
     that
    1.53
     дорогой
    1.53
    Activations Density 0.015%

    No Known Activations