© 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. 10-GEMMASCOPE-RES-131K
    7. 164
    Prev
    Next
    INDEX
    Explanations

    product features and descriptions

    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
     gewiß
    -1.67
     mépris
    -1.64
     čím
    -1.61
     Pokud
    -1.52
    ngoing
    -1.49
    }}{
    -1.47
     koncentr
    -1.46
     châssis
    -1.45
    Método
    -1.41
    ecution
    -1.40
    POSITIVE LOGITS
     your
    2.13
     also
    1.95
     with
    1.87
     who
    1.82
     that
    1.70
     always
    1.51
     others
    1.41
    ционер
    1.41
    歳の
    1.39
     the
    1.38
    Activations Density 0.104%

    No Known Activations