© 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. 12337
    Prev
    Next
    INDEX
    Explanations

    return true

    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
     MACHINERY
    0.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
     anhydride
    0.43
     quenched
    0.43
    ازت
    0.42
     attrakt
    0.42
    блиоте
    0.41
    साइटी
    0.40
     Dü
    0.40
    ujourd
    0.39
    POSITIVE LOGITS
    [
    0.49
    Default
    0.45
    defaults
    0.42
    Home
    0.42
    handle
    0.41
    Dem
    0.40
    DEFAULT
    0.40
     [
    0.40
    Basic
    0.38
     Home
    0.38
    Activations Density 0.001%

    No Known Activations