Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8757
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible

    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
    Ű
    -0.78
     детства
    -0.73
     penurunan
    -0.70
    ometra
    -0.69
     potentially
    -0.68
     покрытие
    -0.68
     September
    -0.68
     decreased
    -0.67
     rá
    -0.67
    鈿
    -0.66
    POSITIVE LOGITS
    Через
    0.77
     Pert
    0.72
     oily
    0.70
    милия
    0.70
     Applicability
    0.69
     Viro
    0.69
     favorita
    0.68
     Infor
    0.68
     RSC
    0.66
     ald
    0.66
    Activations Density 0.049%

    No Known Activations