© 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. 82876
    Prev
    Next
    INDEX
    Explanations

    dates and centuries

    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
    いわゆる
    -1.17
     five
    -1.11
     dozens
    -1.05
     twelve
    -1.03
     two
    -1.00
     constitute
    -1.00
     three
    -0.98
    当時は
    -0.95
     thirty
    -0.95
     four
    -0.94
    POSITIVE LOGITS
     nineteenth
    1.90
     eighteenth
    1.69
     XIX
    1.62
     XVIII
    1.57
     Victorian
    1.48
     medieval
    1.43
     XVII
    1.31
     centuries
    1.29
    江戸
    1.27
     seventeenth
    1.22
    Activations Density 0.186%

    No Known Activations