© 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. 3630
    Prev
    Next
    INDEX
    Explanations

    football and ball skills

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

    The neuron strongly activates on mentions of “ball” (and closely related football terms).

    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
     kilomètres
    -0.91
    wachsene
    -0.86
    Pue
    -0.85
     Tactical
    -0.83
     Dollars
    -0.82
     uuid
    -0.82
    wendige
    -0.81
    neue
    -0.81
     Passes
    -0.80
    
    -0.79
    POSITIVE LOGITS
     carrier
    1.16
     in
    0.94
     laces
    0.93
     notable
    0.92
     carriers
    0.91
    baz
    0.90
    訓練
    0.89
    carrier
    0.89
    証券
    0.88
     whenever
    0.88
    Activations Density 0.011%

    No Known Activations