© 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. 8437
    Prev
    Next
    INDEX
    Explanations

    Ebro, USA, Izmir, Kubota, Crystal

    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
    :");
    -2.14
    .");
    -1.91
     ");
    -1.81
    幛
    -1.80
    ...");
    -1.76
    ');
    -1.76
     \
    -1.73
    鰱
    -1.69
     >",
    -1.67
     ';
    -1.67
    POSITIVE LOGITS
     of
    2.31
     new
    1.66
    0
    1.62
     #
    1.62
    '
    1.53
    to
    1.50
    不高
    1.48
    f
    1.45
    !
    1.44
    ↵
    1.34
    Activations Density 0.096%

    No Known Activations