© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102226
    Prev
    Next
    INDEX
    Explanations

    AsyncTask and related programming constructs

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

    references to asynchronous task operations and classes in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is looking for references to asynchronous execution constructs (e.g. AsyncTask, execute(), callbacks, Workers, threads).

    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
     bricolaje
    -1.45
    却没有
    -1.45
     soldadura
    -1.43
    柃
    -1.42
     danske
    -1.39
    Подробнее
    -1.38
     allah
    -1.30
     pérd
    -1.30
    売上
    -1.29
    箪
    -1.29
    POSITIVE LOGITS
     to
    1.97
    Our
    1.49
     then
    1.45
    </u>
    1.44
     little
    1.43
     so
    1.40
     Aussehen
    1.38
     głównie
    1.35
     όμως
    1.35
    Their
    1.35
    Activations Density 0.007%

    No Known Activations