© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10059
    Prev
    Next
    INDEX
    Explanations

    financial and government data sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haitian
    1.16
    作為
    1.04
     -$
    1.03
     acá
    1.02
     Сурикова
    1.00
     作为
    0.99
    OSU
    0.98
     Суриков
    0.98
     đây
    0.97
     WASHINGTON
    0.97
    POSITIVE LOGITS
     Lancashire
    1.24
     Gloucestershire
    1.21
    uddersfield
    1.20
     Yorkshire
    1.20
    Counc
    1.14
     HMRC
    1.12
    Cllr
    1.11
    £
    1.11
     Tesco
    1.10
     Warwickshire
    1.09
    Activations Density 0.133%

    No Known Activations