© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245081
    Prev
    Next
    INDEX
    Explanations

    copyright, installation, analyses, taxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ރ
    0.44
     انك
    0.44
    樎
    0.44
    ྃ
    0.43
     ভাষণ
    0.43
    spacePad
    0.42
     ট্রেনে
    0.42
     ಅನುಪ
    0.41
    ান্ত্রিক
    0.41
    ⼒
    0.41
    POSITIVE LOGITS
    th
    0.48
    bb
    0.48
    ostar
    0.48
    ok
    0.48
     root
    0.46
    um
    0.46
    op
    0.46
     sq
    0.45
     sya
    0.45
    app
    0.44
    Activations Density 0.000%

    No Known Activations