© 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. 98859
    Prev
    Next
    INDEX
    Explanations

    sports and foreign words

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

    demonstrate positive interactions

    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
     refrain
    0.47
    _
    0.47
    _/
    0.45
    unnel
    0.43
    unger
    0.43
    وز
    0.42
    ellum
    0.41
    NOR
    0.41
    INATION
    0.40
    腊
    0.40
    POSITIVE LOGITS
     sportsman
    0.57
     asta
    0.49
     спорта
    0.49
     tämä
    0.49
     sportsmen
    0.49
     랜
    0.48
    ದಗ
    0.48
     腕時計
    0.47
     sporty
    0.47
     노동
    0.47
    Activations Density 0.000%

    No Known Activations