© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3774
    Prev
    Next
    INDEX
    Explanations

    boxing, boxer, 🥊

    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_all/layer_41_width_262k_l0_big
    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
    acetyl
    0.48
     merged
    0.45
     жыл
    0.45
    ₡
    0.43
    silyl
    0.43
    माल
    0.42
    рку
    0.41
    ὗ
    0.41
    ន្ទ
    0.41
    धारकों
    0.40
    POSITIVE LOGITS
     boxing
    2.66
     Boxing
    2.48
    Boxing
    2.41
     boxer
    2.17
    boxing
    2.13
     boxers
    2.09
    🥊
    1.97
     Boxer
    1.89
    拳
    1.83
     boxe
    1.77
    Activations Density 0.004%

    No Known Activations