© 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. 58759
    Prev
    Next
    INDEX
    Explanations

    payment method and charges

    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
     typology
    -0.87
     Showers
    -0.84
    antikan
    -0.81
     
    -0.80
    registro
    -0.76
     illustrationer
    -0.75
     tapas
    -0.75
     hưng
    -0.74
     câble
    -0.74
    vají
    -0.73
    POSITIVE LOGITS
    Orders
    1.11
    Customers
    0.90
     Region
    0.90
    region
    0.87
     Shi
    0.86
     Territory
    0.83
     Supplier
    0.83
     Order
    0.83
    Employees
    0.83
    Concurrency
    0.82
    Activations Density 0.038%

    No Known Activations