© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47520
    Prev
    Next
    INDEX
    Explanations

    causes consequences, issues, or changes

    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
    薷
    -1.54
     pérd
    -1.53
    medriver
    -1.46
    kurat
    -1.46
     actuelles
    -1.38
     récentes
    -1.31
    жена
    -1.30
     ſte
    -1.30
     You
    -1.27
    aibo
    -1.27
    POSITIVE LOGITS
     in
    2.83
     on
    2.05
    );
    1.70
     by
    1.70
     dėl
    1.57
     for
    1.48
    }{
    1.47
    ){
    1.44
     because
    1.41
     with
    1.39
    Activations Density 0.119%

    No Known Activations