© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34991
    Prev
    Next
    INDEX
    Explanations

    wiki followed by /

    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
     from
    -1.26
     that
    -1.20
    phans
    -1.05
     in
    -1.05
     others
    -1.04
    *,
    -1.01
     their
    -0.99
    lijkse
    -0.99
     for
    -0.98
    ostringstream
    -0.96
    POSITIVE LOGITS
     پنجم
    1.29
    Deine
    1.22
     consacré
    1.20
     schuhe
    1.20
    unuz
    1.20
     nameof
    1.19
     occuper
    1.19
    Themen
    1.18
     ángulo
    1.14
     />';
    1.14
    Activations Density 0.007%

    No Known Activations