© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38548
    Prev
    Next
    INDEX
    Explanations

    reminder of memory

    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
    Negative Logits
     there
    -1.70
    ."
    -1.56
     "
    -1.55
     '
    -1.54
            
    -1.52
        
    -1.44
     `
    -1.44
     występu
    -1.34
     friends
    -1.33
    .
    -1.30
    POSITIVE LOGITS
     that
    1.42
    ± 
    1.39
     båda
    1.38
     månader
    1.37
    袿
    1.33
     čty
    1.29
    udahkan
    1.28
     cheminée
    1.27
     primeiras
    1.27
     varandra
    1.27
    Activations Density 0.028%

    No Known Activations