© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59027
    Prev
    Next
    INDEX
    Explanations

    World's Exposition

    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
    ytt
    -0.77
    fanart
    -0.76
     infecciones
    -0.73
     nasceu
    -0.71
    えました
    -0.70
    ڕ
    -0.68
    urata
    -0.67
    balah
    -0.67
    στα
    -0.66
    immen
    -0.66
    POSITIVE LOGITS
     World
    2.45
     Expo
    2.16
     Worlds
    1.93
    World
    1.92
     Exposition
    1.79
    Expo
    1.73
     expo
    1.65
     exposition
    1.63
     WORLD
    1.63
    Exposition
    1.58
    Activations Density 0.012%

    No Known Activations