© 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. 102579
    Prev
    Next
    INDEX
    Explanations

    league play and competition

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

    The neuron fires on words naming sports leagues, divisions, or conferences (e.g. “Atlantic Division,” “ACC,” “conference,” “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
    job
    -0.76
    梭
    -0.70
    ipers
    -0.70
     freckles
    -0.69
    Filme
    -0.69
     priesthood
    -0.69
    working
    -0.69
     touristique
    -0.68
    
    -0.67
     érde
    -0.66
    POSITIVE LOGITS
     play
    4.19
    play
    3.00
    Play
    2.64
     action
    2.39
     competition
    2.38
     Play
    2.36
     gameplay
    2.30
     PLAY
    2.14
    PLAY
    2.02
    Competition
    1.87
    Activations Density 0.055%

    No Known Activations