© 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. 32718
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and code snippets

    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
    Negative Logits
    क्रम
    -0.80
     прото
    -0.77
    कल
    -0.77
    娉
    -0.76
    レーキ
    -0.76
    都要
    -0.76
     зависит
    -0.74
    contextMenu
    -0.73
    raded
    -0.72
     depends
    -0.71
    POSITIVE LOGITS
     ']
    0.84
    撮り
    0.77
     comporte
    0.76
    模样
    0.75
     './
    0.75
     reż
    0.73
     ubicada
    0.73
    το
    0.73
     Begriffe
    0.73
    热的
    0.73
    Activations Density 0.063%

    No Known Activations