© 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. 22-GEMMASCOPE-RES-131K
    7. 25658
    Prev
    Next
    INDEX
    Explanations

    protected override

    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_22/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
    不断的
    -1.54
     povezave
    -1.52
    鴴
    -1.47
    setCellStyle
    -1.33
     splet
    -1.25
    耳机
    -1.25
    壜
    -1.25
    duled
    -1.23
    炱
    -1.23
    罍
    -1.22
    POSITIVE LOGITS
     of
    1.68
    ,
    1.48
     (
    1.39
    -
    1.39
    However
    1.33
    —
    1.30
    .
    1.23
    ’
    1.23
    Each
    1.20
    !
    1.20
    Activations Density 0.001%

    No Known Activations