© 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. 127852
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and improvements

    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
     or
    -1.45
     if
    -1.38
     should
    -1.35
     but
    -1.33
     for
    -1.23
     makkelijk
    -1.15
     ervaring
    -1.14
    魇
    -1.12
     gemakkelijk
    -1.11
    但是
    -1.10
    POSITIVE LOGITS
     improved
    2.28
     improvements
    1.80
     Improved
    1.73
    Improved
    1.70
    improved
    1.61
     improvement
    1.48
     now
    1.45
     better
    1.43
     теперь
    1.39
    くなった
    1.39
    Activations Density 0.036%

    No Known Activations