© 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. 64405
    Prev
    Next
    INDEX
    Explanations

    ground and signal enhancement

    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
     вона
    -1.46
     hongos
    -1.45
    だいぶ
    -1.28
    はじめまして
    -1.25
     pretože
    -1.23
    もうすぐ
    -1.23
    Składniki
    -1.23
    Forrás
    -1.23
    瞜
    -1.22
     tatsächlich
    -1.20
    POSITIVE LOGITS
     in
    1.64
     on
    1.48
     at
    1.33
    :
    1.25
     is
    1.23
     if
    1.23
     while
    1.19
     separ
    1.13
     toda
    1.09
     duties
    1.09
    Activations Density 0.085%

    No Known Activations