© 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. 56775
    Prev
    Next
    INDEX
    Explanations

    seeing and sights

    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
     仕様
    0.39
    镙
    0.38
    瘩
    0.38
    verte
    0.38
    UTICAL
    0.38
    uridad
    0.38
    öt
    0.38
    ُل
    0.38
    uckle
    0.37
     Bezeichnung
    0.37
    POSITIVE LOGITS
     sight
    0.63
     👀
    0.61
    👀
    0.61
     Sight
    0.60
    Sight
    0.55
    sight
    0.54
    seer
    0.47
     sights
    0.46
    seeing
    0.46
    дай
    0.41
    Activations Density 0.001%

    No Known Activations