© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58184
    Prev
    Next
    INDEX
    Explanations

    synchronization primitives

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

    The main thing this neuron does is detect references to synchronization and concurrency primitives (e.g. imports and uses of “sync,” “WaitGroup,” “notify,” 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
     paramètres
    -0.75
    łóż
    -0.75
    breve
    -0.75
    꺼
    -0.75
     godziny
    -0.71
    짤
    -0.71
     Crunchy
    -0.71
    çim
    -0.70
     jaki
    -0.70
     worsened
    -0.70
    POSITIVE LOGITS
     barrier
    1.70
     Barrier
    1.52
    Barrier
    1.44
     gate
    1.40
     barriers
    1.34
    barrier
    1.27
     latch
    1.23
     CountDown
    1.19
     gates
    1.16
     await
    1.14
    Activations Density 0.008%

    No Known Activations