© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28167
    Prev
    Next
    INDEX
    Explanations

    file dialog chooser

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

    This neuron detects mentions of dialog‐related UI components (tokens like “Dialog,” “ShowDialog,” “FileDialog,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    gulation
    -1.14
     државе
    -1.00
    好像
    -0.99
     piaci
    -0.98
    bewer
    -0.98
    namental
    -0.98
    ))*
    -0.94
     quando
    -0.93
    nament
    -0.93
     Hochsch
    -0.92
    POSITIVE LOGITS
     soliciting
    1.27
     narrowed
    1.05
     selection
    1.04
    ₰
    1.03
     librarian
    1.03
     gestalten
    1.02
    提示
    0.99
     поиска
    0.98
     Retrieves
    0.98
    很久
    0.97
    Activations Density 0.010%

    No Known Activations