© 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. 12399
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    Ꮴ
    -2.42
    𖥧
    -2.22
    趼
    -2.20
    ated
    -2.19
    cych
    -2.14
    溲
    -2.09
     fábricas
    -2.06
    桄
    -2.02
    牴
    -2.00
    毳
    -2.00
    POSITIVE LOGITS
    >
    3.50
    *
    2.97
    [
    2.73
    I
    2.72
    to
    2.67
     Ваш
    2.44
    ?
    2.42
    𖣘
    2.39
    =
    2.23
     Your
    2.20
    Activations Density 0.026%

    No Known Activations