© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13502
    Prev
    Next
    INDEX
    Explanations

    on track

    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_13_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
     세상
    1.28
    让自己
    1.21
    生命的
    1.20
     জনতার
    1.17
     mishaps
    1.14
    诞
    1.14
     luscious
    1.11
    끽
    1.11
    麝
    1.10
     cualidades
    1.08
    POSITIVE LOGITS
    ohar
    1.15
    nPort
    1.09
    Not
    1.06
    kü
    1.06
    zij
    1.05
    Idle
    1.05
    ुर
    1.05
    fisher
    1.04
    私たちは
    1.04
     إ
    1.04
    Activations Density 0.000%

    No Known Activations