© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81635
    Prev
    Next
    INDEX
    Explanations

    scheduling and policies

    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
    hooting
    -0.79
    shooting
    -0.77
    çoise
    -0.74
    ciso
    -0.74
    Crawl
    -0.73
    ってみる
    -0.73
    amante
    -0.72
    cines
    -0.72
    sikker
    -0.72
    irmingham
    -0.71
    POSITIVE LOGITS
     scheduling
    1.89
     policies
    1.63
     policy
    1.61
     Scheduling
    1.47
     scheduler
    1.42
     schedule
    1.37
     algorithm
    1.27
    Scheduling
    1.21
     Policies
    1.20
    policy
    1.18
    Activations Density 0.034%

    No Known Activations