© 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. 127856
    Prev
    Next
    INDEX
    Explanations

    common nouns and their context

    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
     cómodo
    -1.61
     abbin
    -1.53
     pieles
    -1.46
     verur
    -1.40
     repuesto
    -1.40
     soddis
    -1.39
     duradero
    -1.37
     impieg
    -1.37
     pestañas
    -1.36
     hígado
    -1.36
    POSITIVE LOGITS
     in
    2.28
     with
    2.27
     by
    2.25
     to
    2.23
     on
    1.87
     from
    1.79
     for
    1.56
     into
    1.55
     according
    1.54
    もしか
    1.45
    Activations Density 0.107%

    No Known Activations