© 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. 8241
    Prev
    Next
    INDEX
    Explanations

    Poughkeepsie, Doughnut, Cough, sloughing

    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
    -2.80
    一旁
    -2.70
     soo
    -2.63
    猖
    -2.42
    휀
    -2.41
     của
    -2.34
     هناك
    -2.28
    一旁的
    -2.25
     There
    -2.19
    的男人
    -2.17
    POSITIVE LOGITS
    '
    3.08
    "
    2.72
     of
    2.67
    <bos>
    2.58
    屙
    2.52
    ⃨
    2.52
    s
    2.48
    ︲
    2.31
    愎
    2.31
     avaliações
    2.27
    Activations Density 0.012%

    No Known Activations