© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21339
    Prev
    Next
    INDEX
    Explanations

    eye shape

    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
    Negative Logits
     facial
    0.44
     चेहरे
    0.40
    تحان
    0.40
     прозра
    0.40
     সতীশ
    0.39
    鼻
    0.39
    輥
    0.39
     黄
    0.38
     Facial
    0.38
     شفاف
    0.38
    POSITIVE LOGITS
    hape
    0.50
     almond
    0.46
     góc
    0.44
     cat
    0.43
     corner
    0.43
     Wake
    0.42
     Almond
    0.42
     medium
    0.41
    cat
    0.41
     angled
    0.40
    Activations Density 0.006%

    No Known Activations