© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127927
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on sports‐betting jargon—terms like “cover,” “over,” “underdog,” and “favorite.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    odds and differences

    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
    Negative Logits
     to
    -1.30
    andidate
    -1.07
    cestry
    -1.02
    onym
    -1.00
    TableAdapter
    -0.97
    atypes
    -0.95
    ನ
    -0.94
     '_
    -0.93
    ıları
    -0.93
    archical
    -0.91
    POSITIVE LOGITS
     hanno
    1.27
    ímos
    1.04
    crollView
    1.02
     bantuan
    1.02
    комплект
    0.98
    thylamine
    0.98
    참고
    0.98
     belanja
    0.97
     hjälper
    0.97
     they
    0.94
    Activations Density 0.004%

    No Known Activations