© 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. 58230
    Prev
    Next
    INDEX
    Explanations

    from origin

    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
     atracciones
    -1.78
    嗩
    -1.72
     mencionados
    -1.71
     jurado
    -1.67
     obtenidos
    -1.66
     reciclado
    -1.66
    玙
    -1.62
     OGSÅ
    -1.61
     personalizados
    -1.61
    
    -1.59
    POSITIVE LOGITS
     are
    1.93
    er
    1.45
     получила
    1.44
    ”
    1.44
     настолько
    1.39
     blanches
    1.38
     and
    1.34
     for
    1.33
     numberWith
    1.33
     extraordin
    1.32
    Activations Density 0.012%

    No Known Activations