© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30895
    Prev
    Next
    INDEX
    Explanations

    process or worker startup

    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
    Peanut
    -0.76
     الب
    -0.76
    uanya
    -0.74
     веду
    -0.72
     Smol
    -0.70
     japonaise
    -0.69
     Sm
    -0.69
     Troy
    -0.69
     microwave
    -0.68
    ╝
    -0.68
    POSITIVE LOGITS
     workers
    1.85
     worker
    1.77
    workers
    1.47
    Workers
    1.39
    worker
    1.37
     WORKERS
    1.30
     Workers
    1.20
     Worker
    1.16
    Worker
    1.15
     spawn
    1.11
    Activations Density 0.082%

    No Known Activations