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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110534
    Prev
    Next
    INDEX
    Explanations

    function parameters

    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_34/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
     while
    -1.73
    ();
    -1.67
     with
    -1.66
    ;
    -1.66
     (
    -1.61
     for
    -1.61
     at
    -1.60
     as
    -1.58
     during
    -1.56
     and
    -1.55
    POSITIVE LOGITS
    )
    1.77
     mélanger
    1.56
    ){
    1.35
     imprimer
    1.28
     télécharger
    1.25
    "){
    1.23
     maintenant
    1.23
     pè
    1.23
    _)
    1.21
    )
    1.21
    Activations Density 0.037%

    No Known Activations