© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49141
    Prev
    Next
    INDEX
    Explanations

    timers and scheduling code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     leksikon
    -0.79
    DoubleQuotes
    -0.78
     defendants
    -0.77
    öhe
    -0.77
    krivning
    -0.75
    이션
    -0.75
    ografie
    -0.73
     len
    -0.73
    рные
    -0.73
     intens
    -0.72
    POSITIVE LOGITS
    TimerTask
    0.88
     れる
    0.84
     repeats
    0.83
    نجی
    0.82
    Canal
    0.81
     種類
    0.80
    ךְ
    0.79
     ANTI
    0.77
    ਓ
    0.75
     Oates
    0.74
    Activations Density 0.007%

    No Known Activations