© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195071
    Prev
    Next
    INDEX
    Explanations

    special characters and digits

    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
     Akh
    0.40
     auk
    0.40
    澶
    0.40
     제거
    0.39
     Attributes
    0.38
     साक्षी
    0.38
     લક્ષ
    0.38
     bind
    0.38
     jednot
    0.37
     využ
    0.37
    POSITIVE LOGITS
    三重
    0.40
    $">
    0.40
    シャー
    0.39
    newcommand
    0.39
    CTURE
    0.39
    READ
    0.38
    httphttps
    0.38
    Hast
    0.37
    瀝
    0.37
     Connell
    0.37
    Activations Density 0.005%

    No Known Activations