© 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. 16519
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

    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
     ویتامین
    -1.51
    ἵ
    -1.45
    ׇ
    -1.38
     armani
    -1.31
     überweisen
    -1.28
     творо
    -1.27
     already
    -1.20
     garcía
    -1.18
     ترکیه
    -1.16
    Ḏ
    -1.16
    POSITIVE LOGITS
     your
    2.09
    你的
    1.49
     votre
    1.48
    yors
    1.32
    如果你
    1.24
    джу
    1.21
     acerca
    1.19
     spooky
    1.19
     my
    1.17
     Probleme
    1.17
    Activations Density 0.003%

    No Known Activations