© 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. 34-GEMMASCOPE-RES-131K
    7. 70314
    Prev
    Next
    INDEX
    Explanations

    matrices, math, story, chair, row, argmin

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

    The neuron detects tokens associated with LaTeX (or similar) matrix/array environment declarations and delimiters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ុ
    -0.91
     aggregated
    -0.91
    Converters
    -0.87
    ciales
    -0.86
     qualifié
    -0.85
     descrip
    -0.84
     multimeter
    -0.81
     poate
    -0.81
     カレンダー
    -0.81
    Protocols
    -0.79
    POSITIVE LOGITS
    *}[
    0.93
     modern
    0.85
    荼
    0.85
     CORRESPOND
    0.77
    cll
    0.77
    Pairs
    0.75
     Lodge
    0.74
     tutorial
    0.73
     Magic
    0.73
    OOC
    0.73
    Activations Density 0.003%

    No Known Activations