© 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. 34-GEMMASCOPE-RES-131K
    7. 62655
    Prev
    Next
    INDEX
    Explanations

    Scots language

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ktion
    -0.71
    cdot
    -0.70
    moso
    -0.70
     garb
    -0.69
    elli
    -0.68
    ється
    -0.68
     graag
    -0.66
    Wpf
    -0.66
     MySpace
    -0.65
    IDO
    -0.65
    POSITIVE LOGITS
    Fandom
    0.85
    Marshaller
    0.71
     кор
    0.71
    passo
    0.70
    ANSWER
    0.70
     serangga
    0.70
     whatsoever
    0.70
    dengar
    0.69
    Crawler
    0.69
    ights
    0.68
    Activations Density 0.628%

    No Known Activations