© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    wood sprites, Nomadic Matt, dance, great, meth, Michael Scott, matadors, mate assistants, crafting

    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
    JlcG
    2.69
     '~
    2.62
     elevada
    2.59
     professora
    2.58
     direta
    2.57
    ('.
    2.54
     derivada
    2.53
    ならラクマ
    2.51
    {.
    2.50
     nghịch
    2.50
    POSITIVE LOGITS
    aged
    2.69
    romat
    2.43
    oretic
    2.41
    dock
    2.38
    ster
    2.38
    bie
    2.30
    illions
    2.29
    ding
    2.28
    otage
    2.22
    mills
    2.21
    Activations Density 0.479%

    No Known Activations