© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12797
    Prev
    Next
    INDEX
    Explanations

    UK regions and transactions

    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_40_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
     آمریک
    0.68
     آمریکا
    0.66
     アメリカ
    0.66
    ɚ
    0.63
     যুক্তরাষ্ট্রের
    0.62
     अमेरिकी
    0.61
    Thoreau
    0.61
     estadounidense
    0.60
     الأمريكية
    0.60
     Pulitzer
    0.59
    POSITIVE LOGITS
     UK
    1.17
     £
    1.17
     Yorkshire
    1.14
     Cumbria
    1.12
     postcode
    1.10
     Lancashire
    1.08
     영국
    1.05
     British
    1.02
     HMRC
    1.00
     Lincolnshire
    0.99
    Activations Density 0.001%

    No Known Activations