© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128131
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on LaTeX/math notation—Greek letters, backslashes, superscripts, and similar formula tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     intégrée
    -0.94
    turnstile
    -0.93
     inhalation
    -0.93
    
    -0.93
    ковник
    -0.91
     módulos
    -0.91
    osoba
    -0.90
    zoeken
    -0.90
    ആ
    -0.89
     läm
    -0.88
    POSITIVE LOGITS
    r
    0.99
    i
    0.90
    va
    0.88
    u
    0.88
    co
    0.88
    k
    0.84
    𝟓
    0.84
    p
    0.83
    n
    0.83
     then
    0.83
    Activations Density 0.019%

    No Known Activations