© 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. 127923
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     verschillende
    -1.63
     tidligere
    -1.59
     жк
    -1.55
     itong
    -1.51
    értel
    -1.48
     grotte
    -1.48
     prosjek
    -1.48
     énorm
    -1.47
     célè
    -1.45
     ngayon
    -1.45
    POSITIVE LOGITS
     if
    1.73
     to
    1.58
     from
    1.55
     should
    1.55
     without
    1.46
     is
    1.45
     has
    1.45
     on
    1.44
     by
    1.39
     Even
    1.39
    Activations Density 0.016%

    No Known Activations