© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75942
    Prev
    Next
    INDEX
    Explanations

    dispatching actions

    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
     sympathi
    -1.07
     surprising
    -0.95
     cautious
    -0.93
     hars
    -0.91
     Teilen
    -0.90
     Produkten
    -0.88
     společnosti
    -0.87
     Contacts
    -0.87
    ORETICAL
    -0.86
     Projekte
    -0.85
    POSITIVE LOGITS
     dispatcher
    1.23
     Dispatch
    1.22
     Disp
    1.16
    dispatcher
    1.11
    hhh
    1.10
     Dispatcher
    1.07
     bej
    1.02
     dispatch
    0.99
     ē
    0.96
     Karakter
    0.96
    Activations Density 0.005%

    No Known Activations