© 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. 9-GEMMASCOPE-2-RES-16K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    one of, one that

    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_9_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
    1.34
    tedir
    1.10
     związ
    1.05
    ു
    1.01
     núcle
    1.00
     livres
    1.00
     angin
    0.99
    اً
    0.98
     выполнен
    0.96
    िस्थित
    0.95
    POSITIVE LOGITS
    р
    1.27
    ल
    1.22
    যোগে
    1.18
     heck
    1.16
    स्पति
    1.15
     hundred
    1.11
    жды
    1.10
     един
    1.04
    z
    1.00
     liners
    0.97
    Activations Density 0.598%

    No Known Activations