© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13142
    Prev
    Next
    INDEX
    Explanations

    positional margins

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     taller
    0.42
    defi
    0.40
     हाइट
    0.40
    gbm
    0.39
     கிரக
    0.39
     القدر
    0.39
    tall
    0.39
     größer
    0.38
    ڳ
    0.38
    ⨯
    0.38
    POSITIVE LOGITS
     bottom
    0.46
     posterior
    0.40
     industry
    0.39
     drawRight
    0.39
     Top
    0.39
     האח
    0.39
     ends
    0.39
     end
    0.39
     Ends
    0.38
     couch
    0.38
    Activations Density 0.005%

    No Known Activations