© 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. 220048
    Prev
    Next
    INDEX
    Explanations

    parsing plots and functions

    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
     equation
    0.44
     equations
    0.42
     c
    0.40
     T
    0.38
     H
    0.38
    nd
    0.37
     Strategic
    0.37
     Producing
    0.37
     ம
    0.36
     Shiv
    0.36
    POSITIVE LOGITS
     解析
    0.49
     monotonic
    0.49
     parses
    0.49
    解析
    0.47
     parsing
    0.44
     parsley
    0.44
     parse
    0.44
     کولی
    0.44
     monoton
    0.44
    PARSE
    0.44
    Activations Density 0.003%

    No Known Activations