© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21220
    Prev
    Next
    INDEX
    Explanations

    assignment statements

    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
    useNewUrlParser
    -1.89
    mathrm
    -1.80
     ['./
    -1.62
    _
    -1.56
     exemplaires
    -1.55
     gewi
    -1.51
     égard
    -1.48
    است
    -1.48
    </tfoot>
    -1.46
    considered
    -1.45
    POSITIVE LOGITS
     and
    2.25
    </b>
    2.09
    癀
    1.59
    çants
    1.57
    ');
    
    1.56
    Puss
    1.56
     Regi
    1.52
    </h1>
    1.51
     poetas
    1.48
     bagaimana
    1.46
    Activations Density 0.006%

    No Known Activations