© 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. 72354
    Prev
    Next
    INDEX
    Explanations

    predicates following "be"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -2.03
     before
    -1.89
     with
    -1.88
     затем
    -1.80
     through
    -1.78
     without
    -1.78
     where
    -1.77
     what
    -1.68
     about
    -1.66
     based
    -1.66
    POSITIVE LOGITS
    nées
    1.77
     industrie
    1.76
     ultime
    1.67
    鶿
    1.64
     maniere
    1.61
    guarding
    1.61
     упаковке
    1.60
     huile
    1.58
    ኵ
    1.58
     Università
    1.57
    Activations Density 0.018%

    No Known Activations