© 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. 64844
    Prev
    Next
    INDEX
    Explanations

    group, song, activity

    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
     BTS
    0.45
     Kim
    0.44
    oh
    0.41
     Jimin
    0.41
     angel
    0.40
     김
    0.40
    朱
    0.39
    peng
    0.39
    oshima
    0.39
     Oh
    0.39
    POSITIVE LOGITS
     деятельности
    0.65
     деятельность
    0.61
     attività
    0.58
    活動
    0.58
     गतिविधियों
    0.58
    attività
    0.57
     activité
    0.57
     Tätigkeit
    0.57
     activity
    0.56
    莨
    0.56
    Activations Density 0.002%

    No Known Activations