© 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. 67087
    Prev
    Next
    INDEX
    Explanations

    match prediction, drivers download, betting odds

    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
    mbgg
    -1.61
     incredi
    -1.59
     WHILE
    -1.45
    potentially
    -1.45
     Saltar
    -1.45
     також
    -1.45
     centra
    -1.43
     of
    -1.41
     acta
    -1.41
    presumably
    -1.41
    POSITIVE LOGITS
     there
    1.73
     just
    1.64
     four
    1.57
     has
    1.54
     low
    1.48
     any
    1.48
     sehr
    1.46
     their
    1.45
     m
    1.42
     being
    1.42
    Activations Density 0.119%

    No Known Activations