© 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. 38542
    Prev
    Next
    INDEX
    Explanations

    sports teams

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

    The neuron fires on proper-noun phrases naming sports teams or athletic organizations.

    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
     considered
    -1.62
     so
    -1.56
     könnten
    -1.48
     about
    -1.42
    </h4>
    -1.41
     very
    -1.41
     it
    -1.40
     used
    -1.39
     also
    -1.35
     there
    -1.34
    POSITIVE LOGITS
     toiminta
    1.53
     rése
    1.47
    ENING
    1.41
    ጢ
    1.41
    ㄩ
    1.38
    
    1.38
     ANCI
    1.38
    UCTION
    1.37
    呯
    1.37
    🧵
    1.36
    Activations Density 0.082%

    No Known Activations