© 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. 25239
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by 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
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.48
     can
    -1.45
    ($('#
    -1.41
     permiti
    -1.39
     this
    -1.38
     such
    -1.38
     al
    -1.36
     may
    -1.34
     important
    -1.33
     possível
    -1.31
    POSITIVE LOGITS
     oignons
    1.80
    voyez
    1.63
     élas
    1.59
     récents
    1.56
     fidé
    1.55
     estadounid
    1.54
     pantalón
    1.54
     siè
    1.53
     imprimé
    1.52
     coreano
    1.51
    Activations Density 0.383%

    No Known Activations