© 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. 10-GEMMASCOPE-RES-131K
    7. 15826
    Prev
    Next
    INDEX
    Explanations

    different or various language words

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     of
    -2.08
     and
    -1.67
     from
    -1.65
     while
    -1.63
     "
    -1.49
     if
    -1.47
     as
    -1.46
     during
    -1.43
     because
    -1.40
     make
    -1.34
    POSITIVE LOGITS
     разные
    1.95
     respective
    1.91
     olika
    1.77
     разных
    1.70
     różnych
    1.63
     различни
    1.59
     різних
    1.54
     שונים
    1.48
     différentes
    1.46
     különböző
    1.46
    Activations Density 0.191%

    No Known Activations