© 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. 118288
    Prev
    Next
    INDEX
    Explanations

    Hilton hotels

    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
    ли
    -0.78
    TKey
    -0.76
    сси
    -0.76
     listo
    -0.75
    日报
    -0.73
    ра
    -0.71
    віть
    -0.69
    Marshaller
    -0.69
    udy
    -0.68
    ProgressHUD
    -0.68
    POSITIVE LOGITS
     Hilton
    0.88
     Waldorf
    0.87
    Unread
    0.84
     unknownFields
    0.84
    soaked
    0.83
     XCTest
    0.78
     Szene
    0.77
    Hilton
    0.77
    PRODUCT
    0.76
    Děkuji
    0.76
    Activations Density 0.005%

    No Known Activations