© 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. 83808
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases followed by determiners

    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
    llten
    -1.66
    ་་
    -1.65
     porque
    -1.59
    .
    -1.57
    赑
    -1.56
    oció
    -1.55
    куртка
    -1.53
     who
    -1.53
     dámské
    -1.52
     a
    -1.52
    POSITIVE LOGITS
     are
    2.23
     is
    2.17
     will
    1.92
     would
    1.62
    讓你
    1.45
       
    1.44
    such
    1.41
     Your
    1.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.34
     must
    1.32
    Activations Density 0.457%

    No Known Activations