© 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. 24934
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     Traditionally
    -1.01
    ⓔ
    -0.95
    庵
    -0.92
     अपने
    -0.91
     quinto
    -0.90
    Exeunt
    -0.90
     Whereas
    -0.90
    some
    -0.89
     hvilke
    -0.86
     grundsätzlich
    -0.85
    POSITIVE LOGITS
     that
    1.95
     mentioned
    1.52
     they
    1.52
     thing
    1.30
     which
    1.23
     pokaz
    1.19
     thingy
    1.19
     sweter
    1.13
     you
    1.13
     bolsas
    1.11
    Activations Density 0.048%

    No Known Activations