© 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. 7
    Prev
    Next
    INDEX
    Explanations

    roles and identities

    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
    んだから
    -1.83
    жнарод
    -1.54
    </h4>
    -1.45
    ffeine
    -1.45
     allora
    -1.41
     рекомен
    -1.41
    はもう
    -1.40
     nyingi
    -1.38
     then
    -1.37
    setcounter
    -1.35
    POSITIVE LOGITS
     has
    1.69
     lojas
    1.46
    大多数
    1.45
     utilizó
    1.45
     on
    1.41
    翻攝
    1.37
    Život
    1.37
     have
    1.36
    Особенности
    1.31
     is
    1.30
    Activations Density 0.073%

    No Known Activations