© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15881
    Prev
    Next
    INDEX
    Explanations

    latex formulas

    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
    ي
    1.27
    i
    1.05
    י
    1.04
     possibility
    0.98
    稗
    0.96
    يًا
    0.92
    يلا
    0.90
    ി
    0.84
    ি
    0.83
    ሕ
    0.79
    POSITIVE LOGITS
    {(
    1.19
    {$
    0.98
    aciones
    0.97
    {-
    0.96
     luận
    0.93
     pessoas
    0.92
     голе
    0.92
     Freddie
    0.90
     μεγά
    0.88
     altos
    0.88
    Activations Density 0.001%

    No Known Activations