© 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. 127339
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

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

    The neuron is sensitive to LaTeX math syntax, i.e. backslashes and related equation/array 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_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
    -2.06
    Such
    -1.60
    ⚋
    -1.59
     Informações
    -1.56
    Another
    -1.51
     Ensuring
    -1.50
    bilen
    -1.48
    \
    -1.48
     encender
    -1.48
     '\''
    -1.46
    POSITIVE LOGITS
     of
    2.05
    ↵
    2.02
    </b>
    1.80
    他们的
    1.66
     their
    1.65
     você
    1.60
     thier
    1.52
    っていました
    1.48
     â
    1.47
     territorios
    1.47
    Activations Density 0.006%

    No Known Activations