© 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. 59531
    Prev
    Next
    INDEX
    Explanations

    Spanish cities and Morocco

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -2.11
    慙
    -2.05
    "../
    -1.87
    ligators
    -1.80
    槩
    -1.70
    /
    -1.67
     joão
    -1.65
    
    -1.64
     інші
    -1.63
     рекомендуется
    -1.63
    POSITIVE LOGITS
    MessageTagHelper
    1.85
    ↵↵
    1.67
    我們
    1.66
    rientes
    1.66
    tisation
    1.60
    seleccion
    1.57
    
    1.57
     設置
    1.57
    NVIDIA
    1.55
    撓
    1.55
    Activations Density 0.004%

    No Known Activations