© 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. 98775
    Prev
    Next
    INDEX
    Explanations

    class creation with parameters

    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
    ztes
    -1.99
    ！”
    -1.91
     çünkü
    -1.55
    :''
    -1.52
     Organizador
    -1.50
     aproximativ
    -1.48
     یکی
    -1.47
    ophobia
    -1.45
    毕竟
    -1.45
    所谓
    -1.45
    POSITIVE LOGITS
     to
    2.17
     both
    1.88
     with
    1.77
     our
    1.77
    瑒
    1.75
     this
    1.74
     your
    1.68
     either
    1.63
     such
    1.62
    それと
    1.56
    Activations Density 0.019%

    No Known Activations