© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104752
    Prev
    Next
    INDEX
    Explanations

    code and mathematical notation delimiters

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

    LaTeX mathematical commands and symbols, particularly backslash operators like `\bar`, `\cdot`, `\limits`, and other mathematical notation formatting.

    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
    。“
    -1.91
    !”
    -1.57
    /</
    -1.46
    ，“
    -1.46
    ContentLoaded
    -1.45
    ！
    -1.45
    —“
    -1.42
    呖
    -1.41
    рует
    -1.41
     caliente
    -1.38
    POSITIVE LOGITS
     those
    1.77
     more
    1.77
     not
    1.38
    淒
    1.34
     "
    1.34
     these
    1.34
     résoudre
    1.31
     Veel
    1.27
     všetko
    1.26
     войска
    1.24
    Activations Density 0.002%

    No Known Activations