© 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. 41191
    Prev
    Next
    INDEX
    Explanations

    mathbb notation for sets

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

    The neuron activates on LaTeX/math‐mode tokens (backslashes, braces, and math command fragments).

    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
     to
    -2.31
     in
    -2.13
     it
    -2.06
    2
    -1.99
     if
    -1.76
    7
    -1.70
    its
    -1.69
    6
    -1.65
     because
    -1.64
    3
    -1.61
    POSITIVE LOGITS
     каждый
    1.79
     appris
    1.66
     SolutionA
    1.56
     nô
    1.55
    鷂
    1.55
    饜
    1.55
     mauva
    1.52
     sebagainya
    1.52
     otros
    1.51
     océ
    1.51
    Activations Density 0.006%

    No Known Activations