© 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. 10-GEMMASCOPE-RES-131K
    7. 65219
    Prev
    Next
    INDEX
    Explanations

    book titles and exhibition names

    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_10/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
    镲
    -2.13
    Ꮴ
    -1.86
     informaron
    -1.80
    鹇
    -1.77
    
    -1.76
     bepa
    -1.70
     olie
    -1.69
     stiefel
    -1.67
     broek
    -1.66
     ideen
    -1.61
    POSITIVE LOGITS
     on
    2.14
     all
    2.09
     more
    2.03
     several
    1.88
     even
    1.82
     by
    1.80
     in
    1.79
     five
    1.79
     Even
    1.77
     When
    1.77
    Activations Density 0.040%

    No Known Activations