© 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. 40-GEMMASCOPE-2-RES-262K
    7. 132085
    Prev
    Next
    INDEX
    Explanations

    chacha8, chacha20, poly1305

    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
    onda
    0.40
    江湖
    0.37
    >);
    0.36
    oke
    0.35
     ornamented
    0.34
     apparently
    0.34
    slug
    0.34
    ша
    0.33
     vex
    0.33
    polarized
    0.33
    POSITIVE LOGITS
     Combs
    0.40
     সদ্য
    0.39
     بیٹے
    0.39
    Curr
    0.38
    氢
    0.38
     Gọi
    0.38
     চাইলে
    0.37
    Fav
    0.37
     सक्सेस
    0.37
    Specific
    0.37
    Activations Density 0.006%

    No Known Activations