© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5801
    Prev
    Next
    INDEX
    Explanations

    latex document class and packages

    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
    了一个
    1.29
     никогда
    1.16
     сына
    1.15
    ()'
    1.11
     giả
    1.11
    ্যাট
    1.10
    ୩
    1.09
     Asked
    1.08
    ೀತ
    1.08
    ෙහි
    1.05
    POSITIVE LOGITS
    as
    1.79
    ing
    1.58
    es
    1.55
    る
    1.39
    ि
    1.27
    asını
    1.22
     serde
    1.16
     handful
    1.16
    at
    1.16
    is
    1.15
    Activations Density 0.002%

    No Known Activations