© 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. 22-GEMMASCOPE-2-RES-16K
    7. 956
    Prev
    Next
    INDEX
    Explanations

    one-size-fits-all

    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_22_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
    nya
    1.18
     one
    1.14
     одна
    1.05
     ones
    0.95
    দের
    0.93
    mice
    0.92
    า
    0.91
    ด์
    0.90
    一些
    0.90
    отно
    0.89
    POSITIVE LOGITS
     hundred
    1.77
     liners
    1.63
    надцати
    1.60
     sided
    1.59
     heck
    1.57
    ToMany
    1.51
    hundred
    1.50
     lakh
    1.48
    жды
    1.45
    씩
    1.45
    Activations Density 0.193%

    No Known Activations