© 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. 106309
    Prev
    Next
    INDEX
    Explanations

    French descriptive 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
     Being
    -0.88
     elderly
    -0.77
    Being
    -0.75
    挽回
    -0.74
    步驟
    -0.73
    堪能
    -0.73
    ifiques
    -0.71
    ्रिया
    -0.70
     and
    -0.69
     brings
    -0.69
    POSITIVE LOGITS
    usually
    0.83
     geschaffen
    0.82
    iciens
    0.81
     dziś
    0.80
     maggiore
    0.80
     충
    0.80
    τη
    0.80
    🅰
    0.78
    thus
    0.78
    тики
    0.77
    Activations Density 0.003%

    No Known Activations