© 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. 56876
    Prev
    Next
    INDEX
    Explanations

    French words and phrases

    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
     étr
    -1.08
     Sabtu
    -1.02
     информация
    -1.02
     НЕ
    -1.02
     undangan
    -0.96
    salm
    -0.96
    chevrolet
    -0.95
     ਨ
    -0.94
     Thereafter
    -0.94
    mahaman
    -0.94
    POSITIVE LOGITS
     hefyd
    1.01
    нование
    0.99
    mph
    0.94
    │
    0.93
    FOREIGN
    0.93
    seq
    0.91
    避け
    0.90
    AMPLE
    0.90
     بگیرید
    0.89
    Modèle
    0.89
    Activations Density 0.003%

    No Known Activations