© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12796
    Prev
    Next
    INDEX
    Explanations

    competition game terms

    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
     of
    -1.82
    ης
    -1.30
    [
    -1.27
    <
    -1.27
     которые
    -1.20
    owany
    -1.18
    (
    -1.18
    ?
    -1.16
     –
    -1.16
     founded
    -1.15
    POSITIVE LOGITS
     motoru
    1.52
    ärm
    1.45
     envió
    1.44
    珢
    1.40
     öde
    1.39
    pří
    1.38
    Срок
    1.38
     surpre
    1.38
    ضي
    1.37
    嵛
    1.37
    Activations Density 0.017%

    No Known Activations