© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11506
    Prev
    Next
    INDEX
    Explanations

    domain names followed by slashes

    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
    Whitelist
    0.40
     Shopify
    0.39
     शुभारंभ
    0.38
    俻
    0.37
     fromi
    0.36
     அளிக்க
    0.35
     பாராட்ட
    0.35
    逅
    0.35
    cuador
    0.35
    页面存档备份
    0.34
    POSITIVE LOGITS
    //
    0.45
    /
    0.43
     elections
    0.38
     calamities
    0.36
     (
    0.36
    ;
    0.35
     “
    0.34
     conception
    0.33
     ‘
    0.32
     population
    0.32
    Activations Density 0.053%

    No Known Activations