© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11528
    Prev
    Next
    INDEX
    Explanations

    comma or list item

    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_262k_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
     ইত্যাদি
    1.71
     valamint
    1.69
     etc
    1.67
    ع
    1.59
     इत्यादी
    1.59
     както
    1.57
     والأ
    1.54
     odnosno
    1.49
     உள்ளிட்ட
    1.47
     illetve
    1.42
    POSITIVE LOGITS
    "
    1.34
    [
    1.29
    only
    1.11
    MENTS
    1.10
    ...
    1.07
    了一个
    1.06
     celor
    1.06
    员
    1.05
    on
    1.03
    =
    1.02
    Activations Density 0.000%

    No Known Activations