© 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. 10-GEMMASCOPE-RES-131K
    7. 64994
    Prev
    Next
    INDEX
    Explanations

    operatorname usage in math context

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

    The neuron fires on LaTeX “operatorname” tokens (i.e. math‐mode operator name commands).

    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
     alerg
    -1.85
     portuguesa
    -1.81
     estadual
    -1.78
     $('.
    -1.74
     hunde
    -1.72
     português
    -1.71
     GRATU
    -1.70
     ujar
    -1.68
     GARANT
    -1.66
    吀
    -1.64
    POSITIVE LOGITS
    </em>
    2.38
     сдела
    1.91
    to
    1.83
    \
    1.80
     "
    1.73
                
    1.63
    ↵
    1.63
     など
    1.60
     Eigentü
    1.57
    ↵↵
    1.55
    Activations Density 0.146%

    No Known Activations