© 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. 5255
    Prev
    Next
    INDEX
    Explanations

    optic disc cupping

    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
    rale
    0.48
     befri
    0.46
    లే
    0.43
    ड़क
    0.43
    దల
    0.43
    されない
    0.42
     convoluted
    0.42
    atir
    0.39
     Gda
    0.38
    ч
    0.38
    POSITIVE LOGITS
    NOTIFICATION
    0.47
     ذمہ
    0.45
     wszystkie
    0.45
     anteriormente
    0.45
     bezpośred
    0.43
    Built
    0.42
    CEPTION
    0.42
     tất
    0.41
    粈
    0.41
    Existing
    0.41
    Activations Density 0.003%

    No Known Activations