© 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. 10-GEMMASCOPE-RES-131K
    7. 12604
    Prev
    Next
    INDEX
    Explanations

    GUI components and data objects

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

    The neuron detects mentions of GUI container class names (e.g. JPanel, TableLayoutPanel) 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_10/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
     That
    -3.45
    that
    -3.06
     که
    -2.58
    what
    -2.48
    with
    -2.48
    縯
    -2.47
    That
    -2.34
     porsi
    -2.25
    焄
    -2.23
     allow
    -2.14
    POSITIVE LOGITS
    ↵↵
    3.05
     they
    2.78
     famoso
    2.55
    ar
    2.47
    ad
    2.38
    筇
    2.31
     стал
    2.30
    犼
    2.27
     ……
    2.23
     tens
    2.22
    Activations Density 0.001%

    No Known Activations