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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57315
    Prev
    Next
    INDEX
    Explanations

    football clubs and names

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

    This neuron activates on tokens characteristic of professional footballer biographies—especially career-related terms like “football,” “player,” club names, dates, and transfer/join language.

    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
     pripra
    -0.81
    ناول
    -0.80
     カウン
    -0.79
    性命
    -0.76
     evidently
    -0.76
     uží
    -0.74
     metaphysics
    -0.74
    秋田
    -0.73
     Taschen
    -0.73
     initiating
    -0.72
    POSITIVE LOGITS
     FC
    0.80
    ensor
    0.75
     QUICK
    0.74
     сказки
    0.71
     Avis
    0.71
     ACL
    0.71
     مشاه
    0.69
     Hiroshima
    0.69
     sted
    0.69
    ステージ
    0.68
    Activations Density 0.035%

    No Known Activations