© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80286
    Prev
    Next
    INDEX
    Explanations

    boxing

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    onents
    0.53
    cordova
    0.48
    ၂
    0.47
     চরণ
    0.46
    mobilpay
    0.46
    clicks
    0.46
    mere
    0.45
    hetically
    0.44
     defy
    0.44
    knie
    0.44
    POSITIVE LOGITS
     boxing
    0.44
    0.39
    軀
    0.38
     reporting
    0.37
    报告
    0.37
     зві
    0.36
     arg
    0.36
     boxer
    0.36
     répondre
    0.36
     Boxing
    0.36
    Activations Density 0.004%

    No Known Activations