© 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. 45412
    Prev
    Next
    INDEX
    Explanations

    dining table

    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
    깡
    -0.78
     BP
    -0.70
    鳶
    -0.69
     kalla
    -0.69
     locker
    -0.68
     کوت
    -0.68
     towel
    -0.68
    licado
    -0.67
     Татар
    -0.67
    二日
    -0.66
    POSITIVE LOGITS
     table
    3.27
    Table
    2.56
     Table
    2.44
     dining
    2.38
     tables
    2.27
    TABLE
    2.09
     TABLE
    2.06
    table
    2.05
    テーブル
    1.97
     Tables
    1.77
    Activations Density 0.012%

    No Known Activations