© 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. 798
    Prev
    Next
    INDEX
    Explanations

    middle of

    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
    (
    -2.66
    </i>
    -2.50
    [
    -2.33
    -2.28
    卨
    -2.23
    	
    -2.13
    *
    -2.13
    {
    -2.05
     Schritte
    -2.02
    ’
    -2.02
    POSITIVE LOGITS
     attorno
    2.14
    愎
    2.09
    他还
    1.98
     appe
    1.94
     teşekkür
    1.86
     derer
    1.84
    viembre
    1.82
    s
    1.81
     leves
    1.80
    GEBRA
    1.79
    Activations Density 0.006%
    No Known Activations