© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85741
    Prev
    Next
    INDEX
    Explanations

    scientific and code notation

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

    The neuron selectively fires on LaTeX/math‐style font or symbol commands (e.g. “mathsf{…},” smallcaps, superscript markers) rather than ordinary text.

    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
    ↵
    -2.89
     at
    -2.28
     for
    -2.05
     there
    -1.95
    $
    -1.91
     or
    -1.88
    1
    -1.83
    On
    -1.77
    4
    -1.77
     that
    -1.76
    POSITIVE LOGITS
    笵
    2.19
    鹛
    2.17
    跸
    2.16
    炱
    2.14
    盉
    2.11
    缯
    2.06
    齜
    2.03
    ⢅
    2.00
     juſ
    1.99
     eſſ
    1.99
    Activations Density 0.001%

    No Known Activations