© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4821
    Prev
    Next
    INDEX
    Explanations

    sports and games

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

    The neuron strongly activates on words naming sports or athletic activities (e.g. “football,” “soccer,” “baseball,” “participant,” “player,” “athletic,” “sports,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﮑ
    0.86
     lucr
    0.82
     secondi
    0.73
     standout
    0.73
    ті
    0.72
     firm
    0.69
     firme
    0.69
     shave
    0.68
     wobble
    0.68
    ל
    0.68
    POSITIVE LOGITS
    足球
    1.52
     voetbal
    1.38
    football
    1.33
    tennis
    1.27
     फुटबॉल
    1.26
     basketball
    1.25
     क्रिकेट
    1.25
    basketball
    1.23
     футбо
    1.19
     badminton
    1.16
    Activations Density 0.165%

    No Known Activations