© 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. 34-GEMMASCOPE-RES-131K
    7. 34871
    Prev
    Next
    INDEX
    Explanations

    $L^p$ spaces and mathematical symbols

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

    The neuron fires on LaTeX/math‐style tokens (e.g. dollar signs, braces, operators, numbers) marking formula components.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    cern
    -0.82
    ではまた
    -0.81
     Einstein
    -0.81
     move
    -0.74
     código
    -0.73
    msford
    -0.72
     selling
    -0.71
     agrícolas
    -0.70
     introduced
    -0.70
     moving
    -0.70
    POSITIVE LOGITS
     внимательно
    0.79
    logisch
    0.79
     Goh
    0.75
    ٢
    0.75
    cta
    0.73
     undertakings
    0.73
     etap
    0.72
    klär
    0.72
    EMO
    0.71
    上限
    0.71
    Activations Density 0.017%

    No Known Activations