© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83834
    Prev
    Next
    INDEX
    Explanations

    division two, a double

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

    The neuron flags mentions of a specific sports league or division title, especially in football (e.g. “Division Two,” “Northern Premier League,” “North West Counties Football League”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Einzelnachweise
    -0.85
     sab
    -0.82
    Werdegang
    -0.77
    baye
    -0.77
    맛
    -0.76
    jekt
    -0.76
     godine
    -0.75
     ago
    -0.74
    agner
    -0.73
    AuthContext
    -0.73
    POSITIVE LOGITS
     fch
    0.83
     Menlo
    0.82
     impati
    0.78
     excavator
    0.78
     coser
    0.77
     canin
    0.75
     Brochure
    0.75
     leonardo
    0.73
     recommandations
    0.73
     bles
    0.73
    Activations Density 0.033%

    No Known Activations