© 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. 12-GEMMASCOPE-2-RES-16K
    7. 420
    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_12_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
     Committees
    0.74
     myocytes
    0.71
     crumbs
    0.70
    الص
    0.70
     conduits
    0.69
    ש
    0.69
     gird
    0.67
     trademarks
    0.66
     luxuries
    0.66
    ال
    0.66
    POSITIVE LOGITS
    ﻨ
    0.93
    ﺘ
    0.89
    ﺖ
    0.86
    ﻞ
    0.86
    𝐢
    0.84
    ﻴ
    0.84
    ﺰ
    0.83
    чини
    0.81
    ﺪ
    0.80
    szer
    0.80
    Activations Density 0.551%

    No Known Activations