© 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. 123885
    Prev
    Next
    INDEX
    Explanations

    clear followed by assertion

    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
     десять
    -1.90
                
    -1.88
     sly
    -1.87
     to
    -1.87
    
    -1.81
     浪漫
    -1.76
     ats
    -1.75
    hending
    -1.66
    {
    -1.65
    裢
    -1.64
    POSITIVE LOGITS
     that
    1.95
     stated
    1.88
    '
    1.86
     dubbed
    1.85
     deschis
    1.72
     detalj
    1.70
     which
    1.68
     designated
    1.64
     verschill
    1.63
     cykel
    1.62
    Activations Density 0.011%

    No Known Activations