© 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. 34-GEMMASCOPE-RES-131K
    4. 81136
    Prev
    Next
    INDEX
    Explanations

    Big Oste Evolutionary

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

    Python threading and multiprocessing modules and related code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects references to concurrency-related modules and constructs (e.g. threading, multiprocessing, Pool, Thread, Lock) in code.

    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
     свадь
    -0.80
    MessageBox
    -0.73
    quoise
    -0.73
    MigrationBuilder
    -0.69
     reaccion
    -0.66
    Iterations
    -0.65
    coaster
    -0.65
    ера
    -0.65
     Publication
    -0.63
    jestel
    -0.63
    POSITIVE LOGITS
    SKIP
    0.73
    Observer
    0.71
     Gower
    0.68
    こちら
    0.66
     Ryu
    0.66
    困难
    0.66
     chồng
    0.66
    ssf
    0.66
     状態
    0.65
    blok
    0.65
    Activations Density 0.053%

    No Known Activations