Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57
    Prev
    Next
    INDEX
    Explanations

    subscribe with scheduler or thread

    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
    IInterface
    -0.78
     luck
    -0.77
     Lucky
    -0.76
     coincidence
    -0.73
    窯
    -0.71
     coincident
    -0.70
     lucky
    -0.70
    rint
    -0.69
     canlynol
    -0.69
     Luck
    -0.69
    POSITIVE LOGITS
     scheduler
    1.57
     Scheduler
    1.56
     Sched
    1.55
     sched
    1.49
    Scheduler
    1.43
    scheduler
    1.42
    线程
    1.16
     thread
    1.13
    Schedulers
    1.11
     SCHED
    1.09
    Activations Density 0.022%

    No Known Activations