© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    េះ
    0.37
    ")):
    0.32
    Acknowledg
    0.31
    孑
    0.31
    思维
    0.31
    كبر
    0.31
    Downward
    0.31
    =","><
    0.30
    ristmas
    0.30
     اړ
    0.30
    POSITIVE LOGITS
    using
    0.44
     using
    0.44
     class
    0.42
     Program
    0.41
    Console
    0.41
     Console
    0.39
     StreamWriter
    0.38
     konz
    0.37
     Dictionary
    0.37
    class
    0.37
    Activations Density 0.003%

    No Known Activations