© 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. 42468
    Prev
    Next
    INDEX
    Explanations

    programming keywords and values

    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
    ist
    -2.70
    );
    -2.47
     be
    -2.30
    u
    -2.22
    ot
    -2.14
    ara
    -2.09
    o
    -2.09
    f
    -2.08
    ro
    -2.08
    ok
    -2.06
    POSITIVE LOGITS
    廡
    2.58
    騭
    2.55
    怱
    2.36
     Empfindung
    2.34
    一個
    2.28
     terzo
    2.25
     Ausführungen
    2.22
     چیست
    2.22
    相変わらず
    2.19
     frete
    2.17
    Activations Density 0.017%

    No Known Activations