© 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. 69854
    Prev
    Next
    INDEX
    Explanations

    pattern and marker

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

    The neuron activates on mentions of Qt GUI class names (e.g. QCheckBox, QComboBox, QPushButton, QLineEdit, 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_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
    льники
    -0.79
    TEL
    -0.79
     Fotografie
    -0.77
    ENSA
    -0.74
    PIECE
    -0.73
     TEL
    -0.71
    terung
    -0.70
     {:.
    -0.69
     Occident
    -0.69
     Minnie
    -0.68
    POSITIVE LOGITS
     patterns
    1.14
     Patterns
    1.08
     pattern
    0.95
    patterns
    0.93
     Dash
    0.89
    Patterns
    0.86
     opty
    0.84
     Pattern
    0.80
     marker
    0.79
    pattern
    0.79
    Activations Density 0.008%

    No Known Activations