© 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. 9362
    Prev
    Next
    INDEX
    Explanations

    seeing

    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
    thememanager
    0.41
     सत्यापन
    0.39
    шил
    0.38
     dernières
    0.38
    ීර
    0.37
    ให้บริการ
    0.37
     кантора
    0.37
    吩
    0.36
     relied
    0.36
     usługi
    0.36
    POSITIVE LOGITS
     seeing
    1.49
     sees
    1.47
     see
    1.36
     Seeing
    1.36
    Seeing
    1.30
     Sees
    1.26
    seeing
    1.25
     увидеть
    1.25
     melihat
    1.23
     видеть
    1.23
    Activations Density 0.003%

    No Known Activations