© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38963
    Prev
    Next
    INDEX
    Explanations

    Programming language definitions

    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
    '
    -1.39
     pidió
    -1.31
    &#
    -1.31
     if
    -1.30
     indien
    -1.28
    y
    -1.27
     a
    -1.19
    So
    -1.18
     câteva
    -1.18
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.17
    POSITIVE LOGITS
    ৣ
    1.94
    МІ
    1.74
    faker
    1.60
     he
    1.57
     такие
    1.56
    botines
    1.56
    nora
    1.55
    beyaz
    1.54
     összefoglal
    1.54
    EDEFAULT
    1.52
    Activations Density 0.006%

    No Known Activations