© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    directing the eye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     Deadly
    1.69
     glorious
    1.60
     Delicious
    1.55
     Controvers
    1.51
     Huerta
    1.47
    ­
    1.47
     diverse
    1.46
     Fuentes
    1.46
     Prix
    1.44
     And
    1.44
    POSITIVE LOGITS
    不存在
    1.71
    ➀
    1.63
    是否存在
    1.61
    الط
    1.56
    czną
    1.49
    ①
    1.48
    が存在
    1.47
    จะต้อง
    1.44
     няма
    1.44
    managerpage
    1.43
    Activations Density 0.254%

    No Known Activations