© 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. 11142
    Prev
    Next
    INDEX
    Explanations

    math delimiters or academic Portuguese

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

    This neuron detects LaTeX-style superscript reference or footnote markers of the form “^{(…) },” i.e., a superscripted parenthesized label.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    (
    -3.00
    喼
    -2.83
     \
    -2.63
    針對
    -2.41
    er
    -2.41
    ペース
    -2.34
    ه
    -2.34
     versatile
    -2.27
     verzichten
    -2.25
    劻
    -2.25
    POSITIVE LOGITS
    盉
    2.58
    榦
    2.52
    蹰
    2.52
     anteriormente
    2.50
    蜮
    2.47
     库存
    2.45
    歘
    2.45
    瘜
    2.41
    鎹
    2.41
    álbum
    2.34
    Activations Density 0.003%

    No Known Activations