© 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. 22-GEMMASCOPE-RES-131K
    7. 16738
    Prev
    Next
    INDEX
    Explanations

    Beverly Hills

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -1.54
     at
    -1.54
     this
    -1.37
     Although
    -1.31
     This
    -1.27
     Without
    -1.27
     that
    -1.25
     any
    -1.23
     gives
    -1.22
     blatantly
    -1.22
    POSITIVE LOGITS
     alcune
    1.29
     alcuni
    1.23
     gewisse
    1.19
    菒
    1.16
    
    1.14
     唯美
    1.13
    黉
    1.11
     sooo
    1.10
     ストライプ
    1.08
    美しく
    1.06
    Activations Density 0.031%

    No Known Activations