© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73484
    Prev
    Next
    INDEX
    Explanations

    series expansion involving derivatives

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

    The neuron chiefly fires on tokens from mathematical formulas and series expansions—terms like “Taylor,” “expansion,” “sin,” “cos,” “^,” and other LaTeX‐style math notation.

    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
    reporte
    -0.88
     occuper
    -0.83
    參
    -0.75
    Flask
    -0.75
     parfa
    -0.71
    ≼
    -0.70
    autumn
    -0.69
     handsomely
    -0.69
     sardines
    -0.68
    Cef
    -0.68
    POSITIVE LOGITS
     Taylor
    2.67
    Taylor
    2.19
    taylor
    1.90
     series
    1.85
     Series
    1.80
     taylor
    1.75
    series
    1.72
     TAYLOR
    1.71
     expansion
    1.63
    Series
    1.59
    Activations Density 0.051%

    No Known Activations