© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    Sor acronyms

    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
     Flemish
    0.70
    fou
    0.57
     Waren
    0.55
    🇫
    0.54
    ヴ
    0.54
    Jefferson
    0.53
    cích
    0.52
    鑷
    0.52
     Fou
    0.52
    比利
    0.52
    POSITIVE LOGITS
     Sor
    0.85
     ENS
    0.84
    Sor
    0.79
     Labor
    0.77
     Sup
    0.73
     INR
    0.72
     sor
    0.70
     SOR
    0.70
     UTC
    0.70
    ENS
    0.69
    Activations Density 0.023%

    No Known Activations