© 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. 72246
    Prev
    Next
    INDEX
    Explanations

    ned-

    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
     semblent
    -1.79
     sirop
    -1.70
     aboli
    -1.60
     Spanyol
    -1.59
     Médico
    -1.55
     práticas
    -1.54
     lenovo
    -1.52
    枼
    -1.50
     inverno
    -1.49
    pictured
    -1.49
    POSITIVE LOGITS
     so
    2.03
     as
    1.80
     you
    1.70
    gucigalpa
    1.69
     new
    1.64
     people
    1.61
    我們
    1.59
     we
    1.59
     on
    1.52
     FOR
    1.51
    Activations Density 0.024%

    No Known Activations