© 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. 29154
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and functions

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

    The neuron is detecting LaTeX math markup (e.g. backslashes and commands like “frac” and braces) in the text.

    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
     that
    -1.93
     can
    -1.87
    b
    -1.80
     -
    -1.77
     may
    -1.75
    -
    -1.68
     know
    -1.64
    n
    -1.63
    ,
    -1.60
    v
    -1.59
    POSITIVE LOGITS
     ufe
    1.61
     moft
    1.58
     fhew
    1.53
    𝔓
    1.48
     obfer
    1.48
     kontinu
    1.45
     fuper
    1.45
     車場
    1.43
    ebaran
    1.43
     fevere
    1.42
    Activations Density 0.008%

    No Known Activations