© 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. 57163
    Prev
    Next
    INDEX
    Explanations

    Britain and Britishness

    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
     $
    -0.94
     $\$
    -0.90
    rigated
    -0.88
     state
    -0.88
    ão
    -0.86
     firstly
    -0.86
     federal
    -0.82
     forState
    -0.82
     dependant
    -0.81
     federally
    -0.80
    POSITIVE LOGITS
     UK
    3.08
     British
    3.06
     Britain
    2.92
     England
    2.89
    British
    2.86
    England
    2.86
     London
    2.80
    London
    2.77
    英国
    2.73
    UK
    2.66
    Activations Density 0.417%

    No Known Activations