© 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. 10-GEMMASCOPE-RES-131K
    7. 45613
    Prev
    Next
    INDEX
    Explanations

    sports team names in games

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

    The neuron activates on capitalized plural nouns that are college or professional sports team nicknames (e.g., Tigers, Wildcats, Huskies).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     publicité
    -1.64
    ったり
    -1.58
     parution
    -1.56
    หรือ
    -1.54
     poursuite
    -1.53
     regardé
    -1.53
    asında
    -1.50
     trenes
    -1.49
     simplicité
    -1.48
     fonctionnalité
    -1.47
    POSITIVE LOGITS
    </td>
    1.60
     for
    1.60
    のお
    1.60
     won
    1.51
     has
    1.49
     This
    1.49
    ma
    1.41
      
    1.40
     <
    1.38
     \%}$
    1.36
    Activations Density 0.027%

    No Known Activations