© 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. 14299
    Prev
    Next
    INDEX
    Explanations

    UC or U

    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
    िरिक्स
    0.62
    పథ
    0.61
    ᐟ
    0.60
    𝒗
    0.59
    Mâ
    0.59
    𝑣
    0.58
    没有任何
    0.57
     персона
    0.56
     toner
    0.56
     ヴィ
    0.56
    POSITIVE LOGITS
     UC
    0.61
    UC
    0.60
    ucs
    0.60
    uc
    0.56
    SqlClient
    0.55
    ichtigung
    0.55
    --
    0.55
    ục
    0.55
    acency
    0.54
    uci
    0.53
    Activations Density 0.000%

    No Known Activations