© 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. 87027
    Prev
    Next
    INDEX
    Explanations

    synchronized and monitors

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

    This neuron detects mentions of thread‐synchronization constructs (e.g. “synchronized,” locks, and related sync primitives).

    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
     provocado
    -0.95
     serene
    -0.81
     organizada
    -0.81
     jednou
    -0.78
     enviada
    -0.77
    Gön
    -0.76
     dziecko
    -0.75
    Czech
    -0.75
    Ix
    -0.75
    memor
    -0.74
    POSITIVE LOGITS
     monitor
    1.73
    monitor
    1.63
     monitors
    1.52
     Monitor
    1.34
    Monitor
    1.27
     MONITOR
    1.25
     Monitors
    1.15
     мони
    1.12
     monit
    1.10
    监
    0.98
    Activations Density 0.009%

    No Known Activations