© 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. 34-GEMMASCOPE-RES-131K
    7. 30160
    Prev
    Next
    INDEX
    Explanations

    system threading tasks

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

    It fires on occurrences of “Threading” (as in System.Threading) in code, i.e. namespace imports referencing threading.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    謬
    -0.79
     grou
    -0.77
    Jur
    -0.73
     такъ
    -0.73
     sirve
    -0.73
    جان
    -0.71
     COMO
    -0.71
     serves
    -0.71
    updating
    -0.70
     inexp
    -0.69
    POSITIVE LOGITS
    Threading
    0.92
    threads
    0.92
     Thread
    0.84
     hairline
    0.83
    THREADS
    0.82
     optimale
    0.80
    tasks
    0.80
    thread
    0.80
    DICTION
    0.78
    ,~
    0.77
    Activations Density 0.004%

    No Known Activations