© 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. 99863
    Prev
    Next
    INDEX
    Explanations

    wears clothing

    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
     одежды
    0.61
     jumpsuit
    0.59
     옷
    0.58
     clothing
    0.57
     одежда
    0.57
     لباس
    0.56
     garments
    0.55
     الملابس
    0.54
    옷
    0.54
     vêtements
    0.54
    POSITIVE LOGITS
     wears
    0.76
     wore
    0.75
     wearing
    0.70
     wear
    0.66
     Wearing
    0.63
    Wearing
    0.55
    wearing
    0.55
     carrying
    0.51
     tragen
    0.48
     sporting
    0.46
    Activations Density 0.000%

    No Known Activations