© 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. 74918
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    The neuron fires on LaTeX-style in-line math tokens that start with “(” immediately followed by digits—i.e. it detects the beginning of parenthesized math expressions (like fraction symbols) in TeX markup.

    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
    <td>
    -3.75
    瑧
    -2.84
    0
    -2.77
     imidlertid
    -2.70
    i
    -2.59
     歳
    -2.53
    所以
    -2.50
    푣
    -2.42
    韞
    -2.39
    儈
    -2.38
    POSITIVE LOGITS
    ↵↵
    2.88
     foremost
    2.64
     \&
    2.41
     incite
    2.41
     $(\
    2.33
     —
    2.31
    dzić
    2.25
     reputed
    2.20
     worin
    2.19
     reçu
    2.17
    Activations Density 0.013%

    No Known Activations