© 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. 73685
    Prev
    Next
    INDEX
    Explanations

    code delimiters and values

    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
     on
    -1.98
     in
    -1.96
     for
    -1.91
     also
    -1.79
     Y
    -1.76
     at
    -1.74
     of
    -1.72
     is
    -1.64
     N
    -1.60
     all
    -1.60
    POSITIVE LOGITS
     guir
    1.77
     火鍋
    1.66
    Kabel
    1.65
    Kontra
    1.60
     chaussures
    1.59
    焢
    1.58
     diki
    1.57
     poliuret
    1.53
     garantir
    1.48
     prohi
    1.48
    Activations Density 0.011%

    No Known Activations