© 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. 64611
    Prev
    Next
    INDEX
    Explanations

    programming language declarations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     obuv
    -1.43
     炖
    -1.38
    announced
    -1.36
     réjou
    -1.31
    источник
    -1.31
     saludos
    -1.30
     éton
    -1.28
     dáms
    -1.28
    䥑
    -1.27
    Bjs
    -1.26
    POSITIVE LOGITS
     to
    1.41
     and
    1.25
    ,
    1.23
     all
    1.22
     end
    1.15
     &
    1.09
     /
    1.09
     no
    1.08
     (
    1.08
     t
    1.08
    Activations Density 0.036%

    No Known Activations