© 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. 45547
    Prev
    Next
    INDEX
    Explanations

    Creole, Criollo, national origins

    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
    Negative Logits
     école
    -1.90
     domés
    -1.85
     aéreas
    -1.79
     seguras
    -1.78
     involucrados
    -1.74
     einheit
    -1.74
     рядом
    -1.71
    BindingResult
    -1.70
    🏦
    -1.69
    另一种
    -1.63
    POSITIVE LOGITS
    りは
    1.87
    捽
    1.69
     kemudian
    1.61
    at
    1.57
    一流
    1.55
    י
    1.55
    на
    1.54
    },
    1.52
    Furthermore
    1.52
     поэтому
    1.50
    Activations Density 0.012%

    No Known Activations