© 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. 111257
    Prev
    Next
    INDEX
    Explanations

    end of mathematical expression

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

    This neuron detects LaTeX environment closing commands (i.e. the “\end{…}” sequences).

    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
     in
    -1.66
     by
    -1.63
    然的
    -1.62
     државе
    -1.54
     Nature
    -1.48
     女生
    -1.48
     at
    -1.46
     Time
    -1.45
     男生
    -1.42
    on
    -1.41
    POSITIVE LOGITS
     Spéc
    1.92
    夘
    1.83
    (“
    1.69
     accompagner
    1.57
    を使用
    1.55
     problemet
    1.50
     arriver
    1.50
     intrig
    1.48
    袛
    1.48
     parmi
    1.48
    Activations Density 0.003%

    No Known Activations