© 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. 44690
    Prev
    Next
    INDEX
    Explanations

    athletes and players

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

    athletes, teammates, and footballers

    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
    敎
    0.63
     層
    0.63
    業
    0.60
    質
    0.59
    差異
    0.58
    硃
    0.58
    サーバ
    0.57
    層
    0.57
    鋐
    0.57
     灬
    0.57
    POSITIVE LOGITS
     teammates
    1.03
     teammate
    0.99
     offseason
    0.92
     atletas
    0.89
     athletes
    0.87
     footballer
    0.87
     footballers
    0.85
    球员
    0.84
     atlet
    0.84
     athlete
    0.84
    Activations Density 0.132%

    No Known Activations