© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11277
    Prev
    Next
    INDEX
    Explanations

    code components or variables

    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_22/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
     is
    -1.45
     in
    -1.34
     so
    -1.26
     just
    -1.21
     like
    -1.20
     with
    -1.16
     for
    -1.16
    D
    -1.13
     did
    -1.13
     other
    -1.13
    POSITIVE LOGITS
     mélanger
    1.38
     tromper
    1.32
    legte
    1.25
     "");
    1.21
    unuz
    1.21
     karton
    1.20
    뿡
    1.19
     agir
    1.16
     '/',
    1.16
     coû
    1.15
    Activations Density 0.015%

    No Known Activations