© 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. 45427
    Prev
    Next
    INDEX
    Explanations

    multilingual and specific words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     saad
    -1.76
     and
    -1.75
     mene
    -1.59
     dakika
    -1.55
     tulis
    -1.52
     restoran
    -1.52
     terv
    -1.52
    -&
    -1.52
    Œuvres
    -1.48
    🥰
    -1.46
    POSITIVE LOGITS
    ciaio
    1.78
     sometimes
    1.69
     other
    1.62
     into
    1.61
     notwendig
    1.59
     austere
    1.57
     otra
    1.56
     usually
    1.54
     to
    1.54
     ebenfalls
    1.53
    Activations Density 0.003%

    No Known Activations