© 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. 79311
    Prev
    Next
    INDEX
    Explanations

    football players' names

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

    This neuron detects numeric and statistical entries—especially years, match counts, and other numbers—in structured sports data or infobox–style tables.

    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
     Lymph
    -0.86
     carab
    -0.81
     Bany
    -0.81
    annique
    -0.81
     Musk
    -0.81
    Remaining
    -0.80
     Meny
    -0.79
     Remaining
    -0.79
     Thyme
    -0.79
     errone
    -0.79
    POSITIVE LOGITS
     Commons
    0.78
     permit
    0.77
    AQ
    0.76
    Commons
    0.73
    vile
    0.73
    萃
    0.71
    reson
    0.71
     Dore
    0.70
    fabric
    0.69
     непре
    0.68
    Activations Density 0.031%

    No Known Activations