© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19136
    Prev
    Next
    INDEX
    Explanations

    Win followed by disabled/Win

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.56
     og
    0.43
    ina
    0.43
    য়ার
    0.43
    ’
    0.43
    \
    0.40
    の
    0.40
    가
    0.40
    ∞</
    0.40
    นิยม
    0.39
    POSITIVE LOGITS
     tapestry
    0.50
     keypad
    0.46
     hence
    0.44
     vgl
    0.44
    _;
    0.44
     cd
    0.43
     Bhat
    0.43
     seide
    0.42
    ;//
    0.42
     همچنین
    0.42
    Activations Density 0.005%

    No Known Activations