© 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. 48334
    Prev
    Next
    INDEX
    Explanations

    John Williams

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

    This neuron fires on LaTeX math‐mode tokens (e.g. math commands like “SL” and “\mathrm{d},” braces, and other formula elements).

    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
    there
    -3.64
    0
    -3.16
     There
    -2.88
    It
    -2.81
    </h3>
    -2.78
    With
    -2.72
    7
    -2.66
    寕
    -2.45
    Despite
    -2.45
    </h2>
    -2.45
    POSITIVE LOGITS
    
    2.56
    胳
    2.48
     encontraban
    2.34
    鲽
    2.30
    下意识
    2.28
    を探す
    2.28
    も含
    2.23
     $
    2.23
    が多い
    2.17
     dôle
    2.17
    Activations Density 0.002%

    No Known Activations