© 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. 12641
    Prev
    Next
    INDEX
    Explanations

    brand names with and

    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
    .
    -2.16
     geringen
    -1.83
    </strong>
    -1.73
    完美的
    -1.66
     eléctricas
    -1.63
     zapato
    -1.61
     rús
    -1.57
     revés
    -1.57
     makes
    -1.55
     Konkur
    -1.55
    POSITIVE LOGITS
    +}$
    1.75
     to
    1.66
    CERN
    1.65
    mostly
    1.59
    chemic
    1.56
    </h5>
    1.55
     physi
    1.54
    secutions
    1.52
    蚡
    1.52
    BITDA
    1.51
    Activations Density 0.094%

    No Known Activations