© 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. 10-GEMMASCOPE-RES-131K
    7. 14713
    Prev
    Next
    INDEX
    Explanations

    pandas DataFrame creation and usage

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

    The neuron flags uses of the Pandas DataFrame constructor (i.e. occurrences of “DataFrame(”).

    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
     exhilarating
    -2.83
    1
    -2.77
    俅
    -2.70
    鼍
    -2.63
    蟥
    -2.47
     luscious
    -2.41
     momentous
    -2.41
     ridiculously
    -2.38
     et
    -2.30
     acclaimed
    -2.30
    POSITIVE LOGITS
     because
    2.08
    u
    2.08
     untuk
    2.06
    ئيس
    1.99
     people
    1.97
    所需的
    1.97
    したので
    1.91
    あります
    1.91
     some
    1.90
     nearing
    1.89
    Activations Density 0.005%

    No Known Activations