© 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. 62623
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
     Accesorios
    -1.02
     Dimensiones
    -0.98
     Opiniones
    -0.90
    ælp
    -0.89
     Configuración
    -0.87
     Soporte
    -0.86
    ICIAS
    -0.85
    =${
    -0.84
     てい
    -0.83
    做过
    -0.83
    POSITIVE LOGITS
    bigl
    0.93
    operatorname
    0.91
    　　　　　　　　
    0.89
    roomId
    0.80
     even
    0.76
     @(
    0.75
     этап
    0.74
     familiar
    0.73
    ઃ
    0.73
     厚
    0.72
    Activations Density 0.068%

    No Known Activations