© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78695
    Prev
    Next
    INDEX
    Explanations

    button or command click

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

    This neuron fires on code tokens naming or invoking UI buttons (e.g. “btn…,” Click events, Prev/Next button identifiers).

    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
    依然
    -0.82
    NameLabel
    -0.78
     将
    -0.78
    狸
    -0.77
    nameLabel
    -0.77
    richTextBox
    -0.77
    OOT
    -0.75
     geg
    -0.71
    copg
    -0.71
     oś
    -0.71
    POSITIVE LOGITS
     first
    1.04
     Cancel
    0.96
     First
    0.92
    Refresh
    0.91
    First
    0.89
     new
    0.86
    第一天
    0.85
     cancel
    0.84
     Saves
    0.84
    Records
    0.83
    Activations Density 0.003%

    No Known Activations