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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14630
    Prev
    Next
    INDEX
    Explanations

    Northern England places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    郴
    0.64
     Winchester
    0.62
    贛
    0.61
     Monmouth
    0.61
     திருச்சி
    0.60
     Lampung
    0.59
    赣
    0.58
     Boca
    0.58
     Tallahassee
    0.57
    🏹
    0.57
    POSITIVE LOGITS
     Huddersfield
    1.52
     Bradford
    1.23
    uddersfield
    1.22
     Yorkshire
    1.05
     Leeds
    1.02
    Leeds
    0.99
     Calder
    0.96
     Halifax
    0.96
    Brad
    0.87
     Wakefield
    0.85
    Activations Density 0.035%

    No Known Activations