© 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. 64829
    Prev
    Next
    INDEX
    Explanations

    racing and extreme sports

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

    motocross championship racing

    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
    レザー
    0.48
     туристи
    0.47
     воен
    0.45
    旅游
    0.45
    🚓
    0.45
     полицей
    0.44
    観光
    0.43
     маршру
    0.43
     مسلح
    0.43
    軍
    0.43
    POSITIVE LOGITS
    Racing
    0.62
     Racing
    0.62
     racing
    0.61
     championships
    0.57
     championship
    0.57
    racing
    0.57
     KTM
    0.56
     Championship
    0.55
     enduro
    0.54
     podium
    0.53
    Activations Density 0.084%

    No Known Activations