© 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. 58770
    Prev
    Next
    INDEX
    Explanations

    spire, nave, overexpression

    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
     sentía
    -2.36
    ÇÃO
    -2.31
     thinks
    -2.25
    玧
    -2.25
    hörigen
    -2.23
    把你
    -2.17
    🦫
    -2.17
    غذ
    -2.17
    เกง
    -2.17
    瑧
    -2.16
    POSITIVE LOGITS
    o
    3.05
    I
    2.91
    i
    2.83
    '
    2.66
    {
    2.56
     bizarre
    2.42
     '
    2.41
    mathrm
    2.39
    t
    2.33
    </strong>
    2.31
    Activations Density 0.003%

    No Known Activations