© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129322
    Prev
    Next
    INDEX
    Explanations

    programming constructs and types

    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
     producenta
    -1.60
     vêtements
    -1.52
     coûte
    -1.46
     musia
    -1.41
     précieux
    -1.38
     trésor
    -1.38
    を選択します
    -1.38
     régal
    -1.37
     Coloque
    -1.37
     oferec
    -1.37
    POSITIVE LOGITS
     when
    2.73
     which
    1.91
     for
    1.86
     not
    1.76
     without
    1.75
    ↵↵
    1.66
     as
    1.63
     does
    1.60
     with
    1.59
     or
    1.56
    Activations Density 0.055%

    No Known Activations