© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11796
    Prev
    Next
    INDEX
    Explanations

    LaTeX encoding and compilation

    np_acts-logits-general · gemini-2.5-flash-lite

    encoding declarations, specifically "utf" or "UTF" followed by a hyphen or number (as in UTF-8 encoding specifications).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."
    -2.03
     to
    -1.81
     if
    -1.76
     "
    -1.70
    ,"
    -1.58
     from
    -1.56
     Of
    -1.48
     when
    -1.46
    ↵↵↵↵↵↵
    -1.44
    了很多
    -1.44
    POSITIVE LOGITS
    ulence
    1.66
    warnai
    1.54
    Bisa
    1.52
    嘰
    1.51
    鲠
    1.48
     ander
    1.45
    小行星
    1.44
    龊
    1.43
    斗争
    1.42
     handels
    1.41
    Activations Density 0.001%

    No Known Activations