© 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. 9687
    Prev
    Next
    INDEX
    Explanations

    Formula 1 racing

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

    racing and motorsport events

    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
     സ്ത്രീ
    0.70
    妇女
    0.66
    婦
    0.64
    社會
    0.61
    図書館
    0.59
    ہے
    0.59
    謂
    0.57
    ඃ
    0.57
    疥
    0.56
    潾
    0.56
    POSITIVE LOGITS
     racing
    1.36
     motorsport
    1.24
     Racing
    1.20
     Motorsport
    1.13
     racer
    1.09
     racers
    1.02
    racing
    1.00
     NASCAR
    0.99
     driver
    0.99
     MotoGP
    0.99
    Activations Density 0.124%

    No Known Activations