© 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. 559
    Prev
    Next
    INDEX
    Explanations

    sale, price, discount, bundle

    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
     Sal
    -0.84
     local
    -0.84
     embrague
    -0.83
     воин
    -0.76
     reuniones
    -0.75
     production
    -0.74
     telephone
    -0.73
     расположен
    -0.73
    usor
    -0.73
    teos
    -0.73
    POSITIVE LOGITS
    Bundle
    0.96
     peripherals
    0.95
    گز
    0.93
     bundled
    0.93
     Grado
    0.91
     génie
    0.89
     ски
    0.89
     Fulfillment
    0.88
     комплект
    0.88
     grigio
    0.87
    Activations Density 0.011%

    No Known Activations