© 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. 13078
    Prev
    Next
    INDEX
    Explanations

    Java GUI components

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

    This neuron detects Java Swing key-binding API identifiers and calls (e.g. KeyStroke, getInputMap/ActionMap, put, setFocusable).

    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
     possíveis
    -1.18
     geheim
    -1.16
     què
    -1.15
     посвящен
    -1.13
     próprios
    -1.12
     који
    -1.09
     your
    -1.09
     who
    -1.08
     koning
    -1.08
     detalló
    -1.05
    POSITIVE LOGITS
     besonders
    1.34
    Palmarès
    1.28
    āci
    1.27
     練習
    1.20
    ()));
    1.20
    macOS
    1.19
     WHY
    1.17
    繚
    1.17
    chränk
    1.14
    Література
    1.13
    Activations Density 0.018%

    No Known Activations