© 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. 10-GEMMASCOPE-RES-131K
    7. 100864
    Prev
    Next
    INDEX
    Explanations

    Cells, items, columns, rows

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

    This neuron fires on names of data‐structure or UI properties (e.g. Columns, Rows, Cells, Items, Range, Worksheets) used when accessing table/grid/worksheet objects in code.

    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
     for
    -2.86
     if
    -2.27
     as
    -2.08
     with
    -2.05
     at
    -2.03
     in
    -2.00
     using
    -1.94
     because
    -1.90
    r
    -1.84
     by
    -1.77
    POSITIVE LOGITS
     strikingly
    2.16
     quintessential
    1.86
     więks
    1.81
     ridiculously
    1.80
    僦
    1.77
     startling
    1.75
     nowej
    1.75
     boister
    1.74
    
    1.70
     delightfully
    1.70
    Activations Density 0.009%

    No Known Activations