© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37846
    Prev
    Next
    INDEX
    Explanations

    basketball and sports competitions

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

    basketball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    早餐
    0.43
     अभियंता
    0.42
    颔
    0.42
    Legisl
    0.41
     Legislative
    0.40
     विधे
    0.39
     કૃ
    0.39
    蓑
    0.38
     legislative
    0.38
    Algo
    0.38
    POSITIVE LOGITS
     basketball
    0.78
    Basketball
    0.75
    basketball
    0.74
     Basketball
    0.73
    🏀
    0.63
     hockey
    0.61
     баскетбол
    0.59
    篮球
    0.56
     basket
    0.55
     baskets
    0.54
    Activations Density 0.047%

    No Known Activations