© 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. 10-GEMMASCOPE-RES-131K
    7. 9100
    Prev
    Next
    INDEX
    Explanations

    NBA players and teams

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

    The neuron is triggered by NBA basketball–related proper names (team names and star players).

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

    No Comments

    Negative Logits
    .”
    -2.70
    
    -2.06
    秋天
    -2.03
    ⢊
    -2.03
    ");
    -2.00
    出来て
    -2.00
    犒
    -1.95
    出来ました
    -1.92
    碉
    -1.88
     remainder
    -1.84
    POSITIVE LOGITS
    鬭
    2.05
    梘
    1.92
    蚡
    1.88
    嫱
    1.87
    甞
    1.85
     enquanto
    1.84
    咴
    1.82
    {
    1.70
    却不
    1.69
    UIP
    1.65
    Activations Density 0.005%

    No Known Activations