© 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. 34-GEMMASCOPE-RES-131K
    7. 31878
    Prev
    Next
    INDEX
    Explanations

    pd df DataFrame

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

    The neuron fires on tokens that occur in Python code blocks—especially library import lines and alias uses (e.g. “import pandas as pd,” “pd,” “import requests,” etc.).

    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
    Antal
    -0.85
    Burial
    -0.77
    Bö
    -0.73
    Fiesta
    -0.71
    Durability
    -0.70
     Durable
    -0.70
     redirect
    -0.70
    ßig
    -0.69
    directive
    -0.67
    Directors
    -0.66
    POSITIVE LOGITS
     df
    4.53
    df
    4.47
     dataframe
    3.88
     DF
    3.66
    DF
    3.52
     DataFrame
    3.30
    Df
    3.09
    DataFrame
    3.00
    dataframe
    2.73
     Df
    2.50
    Activations Density 0.134%

    No Known Activations