© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68714
    Prev
    Next
    INDEX
    Explanations

    synchronized and sync keywords

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

    The neuron flags uses of synchronization keywords (e.g. “synchronized” or import of “sync”) in code or text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     birkaç
    -2.02
     見える
    -1.96
    緘
    -1.87
    ⧠
    -1.77
    紇
    -1.72
    </strong>
    -1.72
     několika
    -1.70
    ⚌
    -1.70
    Onion
    -1.66
    튿
    -1.66
    POSITIVE LOGITS
    ed
    2.38
    [
    2.34
    It
    2.30
    only
    2.25
    Not
    2.13
    //
    2.13
    Don
    2.11
    not
    2.08
    8
    2.06
    ",
    2.00
    Activations Density 0.004%

    No Known Activations