© 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. 34-GEMMASCOPE-RES-131K
    7. 94213
    Prev
    Next
    INDEX
    Explanations

    Russian, Japanese, Korean, and English mixed

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Both
    -1.08
    日から
    -1.03
     both
    -0.98
    Svara
    -0.98
     furthering
    -0.97
     típico
    -0.97
    日まで
    -0.96
     until
    -0.96
    Svar
    -0.96
     should
    -0.93
    POSITIVE LOGITS
     aranha
    1.06
    NhanVien
    1.01
    ៍
    0.99
     Woman
    0.98
     hisz
    0.98
    ју
    0.97
     capables
    0.96
     Helping
    0.95
     shores
    0.94
    ikes
    0.94
    Activations Density 0.003%

    No Known Activations