© 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. 104348
    Prev
    Next
    INDEX
    Explanations

    numbers following years

    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
     (
    -2.23
     in
    -1.90
     of
    -1.77
     from
    -1.70
     which
    -1.70
    ;
    -1.65
     ((
    -1.63
     as
    -1.58
    .
    -1.54
     using
    -1.49
    POSITIVE LOGITS
     alcune
    1.95
    ㆆ
    1.81
     accompagner
    1.63
    휀
    1.63
     liegenden
    1.53
    STRUCTION
    1.49
    訁
    1.49
    graphiques
    1.48
     alcuni
    1.47
     ovviamente
    1.47
    Activations Density 0.026%

    No Known Activations