© 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. 10-GEMMASCOPE-RES-131K
    7. 105461
    Prev
    Next
    INDEX
    Explanations

    continents and regions

    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_10/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
    ໊
    -1.79
     nové
    -1.77
    犼
    -1.71
     nového
    -1.61
     nový
    -1.59
     prodej
    -1.59
     Geräten
    -1.55
     desafíos
    -1.54
    などに
    -1.52
     sprawie
    -1.52
    POSITIVE LOGITS
    It
    1.52
    There
    1.48
    According
    1.35
     milyon
    1.27
    During
    1.27
    Through
    1.25
    
    1.23
    Both
    1.21
    Given
    1.21
    時間
    1.18
    Activations Density 0.127%

    No Known Activations