© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4245
    Prev
    Next
    INDEX
    Explanations

    Chicago entities and locations

    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
     картинка
    -0.88
    wisata
    -0.83
    orianCalendar
    -0.79
    riers
    -0.78
    流星
    -0.74
    บุรี
    -0.73
    tsu
    -0.72
     Оп
    -0.72
    tA
    -0.71
    呂
    -0.71
    POSITIVE LOGITS
    Chicago
    1.34
     Cubs
    1.27
     Chicago
    1.27
     CHICAGO
    1.20
     chicago
    1.13
     Windy
    1.09
    Hope
    1.07
     ILLINOIS
    1.01
     芝
    1.00
    hibition
    0.98
    Activations Density 0.009%

    No Known Activations