© 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. 34-GEMMASCOPE-RES-131K
    7. 47115
    Prev
    Next
    INDEX
    Explanations

    stadiums and venues

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on mentions of sports venues (e.g. “the Liberty Stadium,” “the Lane,” etc.), i.e. stadium or arena names and related location references.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     科
    -0.77
     Новый
    -0.73
     інформа
    -0.73
     posibil
    -0.72
    öten
    -0.70
     dimensionless
    -0.69
    updatedAt
    -0.69
     landfills
    -0.69
     Hivatalos
    -0.68
    ВИ
    -0.67
    POSITIVE LOGITS
     Arena
    0.99
     stadium
    0.80
     arena
    0.72
     expense
    0.71
     Oval
    0.71
    Req
    0.70
     evils
    0.70
    jeli
    0.69
    Arena
    0.69
    可不
    0.68
    Activations Density 0.041%

    No Known Activations