© 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. 30736
    Prev
    Next
    INDEX
    Explanations

    product, deliver, value

    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
    ىز
    0.43
    द्योग
    0.42
    maw
    0.39
     laoreet
    0.38
    र्मेंद्र
    0.38
    帜
    0.37
    ږي
    0.36
    Dental
    0.36
     diminta
    0.36
     kullanım
    0.36
    POSITIVE LOGITS
     अनुसार
    0.46
     현재
    0.46
    ->
    0.45
     nào
    0.45
     брак
    0.44
     就是
    0.43
     কতটা
    0.43
    すなわち
    0.43
     円
    0.43
     ಸಾಕಷ್ಟು
    0.42
    Activations Density 0.003%

    No Known Activations