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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2562
    Prev
    Next
    INDEX
    Explanations

    code imports and file paths

    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
    Not in Any Lists

    No Comments

    Negative Logits
    முகச்
    0.30
    मलव
    0.28
    र्सन
    0.28
     सीजीएल
    0.27
     carboxylic
    0.27
    ාල
    0.26
    ार्मिक
    0.26
    鳇
    0.26
    醪
    0.26
     Absolutely
    0.26
    POSITIVE LOGITS
    /
    0.54
    _
    0.52
    utils
    0.45
    /[
    0.39
    /_
    0.39
    /__
    0.38
    _/
    0.38
    __
    0.37
    \
    0.37
    Utils
    0.36
    Activations Density 0.024%

    No Known Activations