© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15090
    Prev
    Next
    INDEX
    Explanations

    package version specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ignty
    0.71
    illos
    0.65
    فاظ
    0.60
    [[
    0.60
    [
    0.59
    Ethan
    0.59
    zicht
    0.59
    pillars
    0.57
    ZF
    0.57
    (\
    0.56
    POSITIVE LOGITS
     "^
    1.34
     "~
    1.05
     "*"
    1.00
     "=
    0.99
     moderate
    0.97
     Moderate
    0.95
     nes
    0.92
     pangkat
    0.92
     yaklaşık
    0.92
     "*
    0.90
    Activations Density 0.002%

    No Known Activations