© 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. 54153
    Prev
    Next
    INDEX
    Explanations

    synchronization in programming contexts

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

    This neuron detects occurrences of the literal string “sync” (in identifiers, code, or XML attributes), i.e. references to synchronization.

    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
    </strong>
    -2.94
    0
    -2.81
     They
    -2.55
    鹮
    -2.53
     same
    -2.39
     terceiros
    -2.23
     probablemente
    -2.19
     siguiendo
    -2.19
    </h4>
    -2.13
     Jeden
    -2.13
    POSITIVE LOGITS
    In
    2.55
    𝐓
    2.48
    ",
    2.31
     είναι
    2.30
    捭
    2.28
    蕷
    2.23
     alin
    2.16
    шивка
    2.14
    ug
    2.13
    ron
    2.13
    Activations Density 0.009%

    No Known Activations