© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    UK and British terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stacy
    0.49
    持久
    0.40
     kich
    0.39
     ህ
    0.39
     stir
    0.38
     트리
    0.38
    丵
    0.38
    plete
    0.37
     Freder
    0.37
    꼐
    0.37
    POSITIVE LOGITS
    Scottish
    0.54
    英国
    0.52
     £
    0.52
    UK
    0.50
     (£
    0.49
    £
    0.49
    London
    0.48
    British
    0.47
     Moreton
    0.47
     Brits
    0.47
    Activations Density 0.000%

    No Known Activations