© 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. 13871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     রাজনী
    0.55
    หา
    0.54
    羅
    0.54
     गाड़ी
    0.53
     หา
    0.53
     Leo
    0.52
     GAO
    0.52
    noc
    0.52
    វា
    0.52
     Tup
    0.51
    POSITIVE LOGITS
    蛭
    0.54
    ⠊
    0.54
     cach
    0.54
    ếm
    0.52
     vean
    0.52
     caché
    0.52
     ভুলে
    0.51
    得知
    0.51
     evenings
    0.50
     распростра
    0.50
    Activations Density 0.000%

    No Known Activations