© 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. 37920
    Prev
    Next
    INDEX
    Explanations

    Cell style property

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

    The neuron activates on code tokens involved in setting fill color or pattern on a spreadsheet cell style (e.g. calls like setFillForegroundColor and setFillPattern)

    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
    ="@+
    -0.87
     asleep
    -0.80
     natten
    -0.77
     showroom
    -0.75
    ilang
    -0.75
     Rossi
    -0.74
    باً
    -0.73
    誓
    -0.73
    記念
    -0.73
    änderungen
    -0.73
    POSITIVE LOGITS
     Cell
    0.96
    dė
    0.91
     cell
    0.90
    Pand
    0.88
     selection
    0.81
    PCell
    0.80
     CELL
    0.79
     сказать
    0.78
    Similarly
    0.77
    ctuation
    0.77
    Activations Density 0.001%

    No Known Activations