© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2723
    Prev
    Next
    INDEX
    Explanations

    program termination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    updating
    0.83
     Updating
    0.81
    Updating
    0.80
    Manipulation
    0.78
    新增
    0.78
    invalidate
    0.75
     actualizado
    0.75
    偐
    0.74
    Subtract
    0.74
    gres
    0.74
    POSITIVE LOGITS
     run
    1.15
    run
    1.06
     startup
    1.03
    mainloop
    1.01
    exit
    0.95
     runApp
    0.95
     Run
    0.94
     exit
    0.94
     start
    0.94
     uruch
    0.94
    Activations Density 1.177%

    No Known Activations