© 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. 24945
    Prev
    Next
    INDEX
    Explanations

    religious places and worship

    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
     применя
    -1.38
    ૉ
    -1.35
     kaplama
    -1.34
     seçenek
    -1.31
     output
    -1.30
     الشاشة
    -1.30
     Flexible
    -1.26
     Industrial
    -1.26
     error
    -1.25
    谩
    -1.25
    POSITIVE LOGITS
     ویتامین
    1.70
     cukru
    1.56
    Ingrédients
    1.38
    ׇ
    1.36
    岁的
    1.36
    ಃ
    1.31
    нование
    1.29
    歳の
    1.27
     besø
    1.23
     włosów
    1.21
    Activations Density 0.052%

    No Known Activations