© 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. 7306
    Prev
    Next
    INDEX
    Explanations

    graphical user interface (GUI)

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

    The neuron activates on references to graphical user interface (GUI) components, frameworks, or setup details (e.g., mentions of GUI, PyQt, LineEdit, widgets).

    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
     EARTH
    -0.78
    काश
    -0.71
    Earth
    -0.69
     promont
    -0.69
    copyWith
    -0.69
     headphones
    -0.69
     услуг
    -0.68
     Tempel
    -0.67
    τές
    -0.67
    指标
    -0.67
    POSITIVE LOGITS
     GUI
    2.55
     gui
    1.95
    GUI
    1.95
     GU
    1.77
     UI
    1.69
    Gui
    1.69
     Gui
    1.66
    gui
    1.63
    GU
    1.52
     ui
    1.38
    Activations Density 0.321%

    No Known Activations