© 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. 64319
    Prev
    Next
    INDEX
    Explanations

    playoff qualification or requirements

    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
    //!
    -1.17
     miró
    -1.05
     nena
    -1.03
     bague
    -1.02
    karet
    -1.02
     выбрать
    -1.02
     it
    -1.01
    蜈
    -1.01
     baca
    -0.98
    vade
    -0.98
    POSITIVE LOGITS
    資料來源
    1.14
    熾
    1.07
    態度
    1.04
    dentro
    1.02
    強烈
    1.01
     sạc
    1.01
    敍
    1.01
    儀式
    0.97
     hyö
    0.94
    VIDEOS
    0.94
    Activations Density 0.001%

    No Known Activations