© 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. 34-GEMMASCOPE-RES-131K
    7. 117198
    Prev
    Next
    INDEX
    Explanations

    administrative divisions and regions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Arquivado
    -0.88
     anivers
    -0.85
     countries
    -0.85
     JURIS
    -0.85
     configurar
    -0.85
     some
    -0.83
    capulco
    -0.82
    uksessa
    -0.82
     дії
    -0.82
     PUBLICATIONS
    -0.81
    POSITIVE LOGITS
     recaudación
    0.91
     remplacé
    0.90
     CIP
    0.90
     ≈
    0.88
     ∈
    0.87
    我想
    0.87
     NUT
    0.86
    Теперь
    0.83
     proletariat
    0.81
    FYI
    0.79
    Activations Density 0.028%

    No Known Activations