© 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. 12788
    Prev
    Next
    INDEX
    Explanations

    shell variables

    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
    т
    3.28
    𝘻
    2.73
     flocked
    2.65
     enkel
    2.56
    ृति
    2.39
    การ
    2.35
    অর্
    2.34
    ت
    2.28
    ي
    2.24
    ください
    2.23
    POSITIVE LOGITS
    ية
    3.03
    GLOBALS
    3.02
    𝑂
    2.95
    querysearch
    2.74
    𝐸
    2.67
    ियों
    2.62
    ination
    2.59
    ${
    2.55
    v
    2.54
    𝐼
    2.52
    Activations Density 0.082%

    No Known Activations