© 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. 70535
    Prev
    Next
    INDEX
    Explanations

    Kush, RSP, Cree, AGU, TSC, heretofore

    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
    翃
    -3.23
    冢
    -2.73
    providedIn
    -2.66
    "
    -2.45
     soothe
    -2.45
    崽
    -2.36
    庐
    -2.33
    the
    -2.31
    enablog
    -2.28
    墻
    -2.28
    POSITIVE LOGITS
    栳
    3.28
    ных
    2.77
     längere
    2.66
    嗞
    2.61
    0
    2.59
    嫱
    2.48
    —“
    2.39
    -“
    2.38
    ᜀ
    2.33
    웻
    2.31
    Activations Density 0.019%

    No Known Activations