© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10813
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office Excel

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

    This neuron responds to mentions of software interface elements (toolbars, menu bars, ribbons, document windows) and their version numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cellules
    0.62
     Zellen
    0.59
     linkCell
    0.59
    区块
    0.57
     Chattanooga
    0.56
     células
    0.56
     Cells
    0.55
    ﹃
    0.55
    zell
    0.54
    Cells
    0.54
    POSITIVE LOGITS
     Office
    0.96
    Office
    0.88
     macros
    0.87
     OFFICE
    0.85
    office
    0.82
     office
    0.81
     Word
    0.81
    docx
    0.79
     Macros
    0.79
     PowerPoint
    0.78
    Activations Density 0.113%

    No Known Activations