© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45039
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     constitué
    -1.06
    varez
    -1.03
     Expend
    -1.02
     merged
    -0.99
    你会
    -0.94
     muerta
    -0.93
     especiais
    -0.93
     behaup
    -0.93
     Consejos
    -0.93
     cuello
    -0.92
    POSITIVE LOGITS
    ImageIO
    1.08
     поставки
    0.91
     it
    0.90
     konkurs
    0.90
     предложи
    0.90
    canActivate
    0.88
    ൻ
    0.87
    IContainer
    0.87
    allowNull
    0.84
     diken
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.