© 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. 34-GEMMASCOPE-RES-131K
    7. 81074
    Prev
    Next
    INDEX
    Explanations

    UI action methods

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

    This neuron fires on Objective-C method declarations marked with the IBAction keyword.

    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
     membag
    -0.91
     pacar
    -0.91
     bloed
    -0.89
    lepaskan
    -0.88
     menunggu
    -0.87
     frumos
    -0.85
     droom
    -0.85
     jesteś
    -0.85
     ouders
    -0.84
     berdua
    -0.84
    POSITIVE LOGITS
     on
    2.56
     onClick
    1.24
    on
    1.13
     On
    1.12
    onClick
    1.10
    =="")
    1.09
     handle
    1.09
     click
    1.04
    ==='
    1.04
    onPressed
    1.01
    Activations Density 0.013%

    No Known Activations