© 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. 22-GEMMASCOPE-RES-131K
    4. 71735
    Prev
    Next
    INDEX
    Explanations

    mathematical notation sequences

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

    The neuron is keyed to LaTeX math markup—i.e. dollar‐sign delimiters, braces, and related tokens that signal a mathematics expression.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -1.57
     from
    -1.52
     during
    -1.38
     at
    -1.32
     any
    -1.28
     through
    -1.26
     before
    -1.23
    ဴ
    -1.23
     of
    -1.22
     with
    -1.17
    POSITIVE LOGITS
     religieux
    1.43
    
    1.32
     you
    1.27
    begins
    1.24
     obviamente
    1.24
     grasas
    1.23
     REALLY
    1.22
     mân
    1.21
    ウト
    1.19
     VERY
    1.19
    Activations Density 0.006%

    No Known Activations