© 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. 55713
    Prev
    Next
    INDEX
    Explanations

    TextField or phrase start

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

    The neuron detects references to GUI text input fields (e.g. occurrences of “text fields,” “JTextField,” “TextField” in code).

    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
    UBS
    -0.71
    CN
    -0.70
    那
    -0.70
    APB
    -0.69
    셨
    -0.69
     موا
    -0.68
    cree
    -0.68
    SizeMode
    -0.68
    াপ
    -0.67
    ibt
    -0.66
    POSITIVE LOGITS
     setText
    1.13
     JTextField
    1.09
    getText
    1.03
    setText
    1.01
    setColumns
    1.01
     tex
    0.94
     getText
    0.91
     Limit
    0.91
    Editable
    0.90
    JTextField
    0.90
    Activations Density 0.005%

    No Known Activations