© 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. 14004
    Prev
    Next
    INDEX
    Explanations

    Canada and its government

    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
     traducciones
    -1.23
    𓆸
    -1.19
     También
    -1.19
     Meningkatkan
    -1.13
     čaj
    -1.12
    одно
    -1.11
    UpdatedBy
    -1.11
     libros
    -1.11
     Cómo
    -1.09
    Carroll
    -1.09
    POSITIVE LOGITS
     canad
    1.21
     Canada
    1.21
    之所以
    1.13
     centrif
    1.10
     sopa
    1.09
    r
    1.06
     proteine
    1.06
     просто
    1.06
     merce
    1.05
     ぷ
    1.05
    Activations Density 0.114%

    No Known Activations