© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8533
    Prev
    Next
    INDEX
    Explanations

    competition or winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soccer
    0.61
    Soccer
    0.60
    🏐
    0.57
    Basketball
    0.55
     Баскетбол
    0.55
     bás
    0.54
    游戏的
    0.54
    敉
    0.53
     Volleyball
    0.52
     كرة
    0.51
    POSITIVE LOGITS
     podium
    0.64
     contenders
    0.57
     verseny
    0.53
     contestants
    0.53
     contender
    0.52
     venced
    0.52
     vying
    0.51
     ganador
    0.51
     competitors
    0.50
     overtook
    0.50
    Activations Density 0.112%

    No Known Activations