© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86734
    Prev
    Next
    INDEX
    Explanations

    calculus notation and math expressions

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

    This neuron fires on single‐letter or small tokens that appear as mathematical variables or symbols within LaTeX/math expressions.

    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
    	
    -2.17
    (※
    -2.16
     first
    -2.09
    ?!
    -2.08
     during
    -2.06
     системи
    -2.03
    ”?
    -2.02
     several
    -2.02
     since
    -1.97
     superbly
    -1.95
    POSITIVE LOGITS
    殽
    2.61
    鹩
    2.50
     a
    2.45
    ᠌
    2.27
    tures
    2.17
    gives
    2.13
    的男人
    2.06
    毟
    2.05
    的黑
    2.02
    鲼
    2.02
    Activations Density 0.014%

    No Known Activations