© 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. 44745
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming symbols

    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
     it
    -1.77
    枚目
    -1.73
     "
    -1.71
     metropolitana
    -1.70
    ほんと
    -1.59
    年も
    -1.52
    ほら
    -1.47
    ztes
    -1.44
    );
    -1.43
     "...
    -1.40
    POSITIVE LOGITS
     in
    1.81
    .}(
    1.77
    ’
    1.70
     \
    1.68
     QtCore
    1.59
    kumpulan
    1.59
     DBNull
    1.57
    </tfoot>
    1.56
     MessageBoxIcon
    1.55
    cloudf
    1.52
    Activations Density 0.053%

    No Known Activations