© 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. 38844
    Prev
    Next
    INDEX
    Explanations

    country, countryside, region

    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
     preparados
    -1.74
     fotografías
    -1.65
     compradores
    -1.57
     registrados
    -1.55
    ！");
    -1.55
     dispuestos
    -1.52
     électronique
    -1.50
    ⍢
    -1.49
     vendedores
    -1.46
     motocicletas
    -1.46
    POSITIVE LOGITS
    (
    1.80
     we
    1.71
    E
    1.70
     :
    1.59
    f
    1.59
     reminds
    1.56
     to
    1.55
    -
    1.54
     area
    1.52
     are
    1.50
    Activations Density 0.057%

    No Known Activations