© 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. 83659
    Prev
    Next
    INDEX
    Explanations

    more about / more on

    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
     две
    -1.90
    lgari
    -1.72
     number
    -1.66
    ()],
    -1.64
     brief
    -1.64
     если
    -1.59
     tratan
    -1.57
    ÍS
    -1.56
     econó
    -1.55
     zunächst
    -1.53
    POSITIVE LOGITS
    d
    2.31
     them
    2.05
     of
    1.62
    '
    1.59
    ing
    1.54
    ang
    1.48
     than
    1.48
     liés
    1.46
    p
    1.45
    acterísticas
    1.44
    Activations Density 0.008%

    No Known Activations