© 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. 73959
    Prev
    Next
    INDEX
    Explanations

    latex and html code

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

    The neuron fires on backslashes that introduce TeX/LaTeX 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
     serán
    -2.03
     we
    -1.99
    ↵
    -1.93
    へ向
    -1.81
    ⸢
    -1.73
     metaphor
    -1.70
     is
    -1.70
    enablog
    -1.66
     será
    -1.63
     estará
    -1.61
    POSITIVE LOGITS
    ización
    2.41
    nosed
    1.81
    antes
    1.80
    现有
    1.80
     définiti
    1.78
    fledged
    1.77
    ícias
    1.77
    推荐阅读
    1.77
    푁
    1.76
     There
    1.75
    Activations Density 0.026%

    No Known Activations