© 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. 26886
    Prev
    Next
    INDEX
    Explanations

    which-path theory, data

    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
    ಪು
    0.37
    碴
    0.37
     захід
    0.36
    ပြ
    0.35
     decena
    0.35
    گیرد
    0.35
     힘
    0.34
     iban
    0.34
    째
    0.34
    HasFieldError
    0.33
    POSITIVE LOGITS
     Abbreviations
    0.44
    tools
    0.41
     OPEN
    0.41
     ARTICLES
    0.41
     opener
    0.40
    Abbreviations
    0.39
     Tools
    0.39
     ARTICLE
    0.38
    esto
    0.38
    OPEN
    0.37
    Activations Density 0.000%

    No Known Activations