© 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. 14606
    Prev
    Next
    INDEX
    Explanations

    gal

    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
     fuzz
    0.62
    ◹
    0.55
     cognitiva
    0.54
     socket
    0.52
    Socket
    0.52
     Socket
    0.52
    ♟
    0.52
     አስ
    0.51
    Sockets
    0.51
     प्रच
    0.50
    POSITIVE LOGITS
     gal
    4.69
     gall
    4.44
     Gal
    4.38
    Gal
    4.31
    Gall
    4.31
    gal
    4.28
     Gall
    4.25
     GAL
    4.22
     gallery
    4.13
    gall
    4.13
    Activations Density 0.176%

    No Known Activations