© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66901
    Prev
    Next
    INDEX
    Explanations

    gnome nautilus manager alsa jack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORMAL
    -1.52
     USDT
    -1.48
    beforeAll
    -1.40
     Helped
    -1.37
     Litecoin
    -1.34
     :"
    -1.31
    "(
    -1.31
     Hashtag
    -1.28
     būs
    -1.28
    และ
    -1.27
    POSITIVE LOGITS
     ‘
    1.35
    Iya
    1.17
     about
    1.17
     teníamos
    1.14
     are
    1.13
     gewöhnlich
    1.13
    ？」
    1.11
     gelungen
    1.08
    </u>
    1.07
    ～～
    1.02
    Activations Density 0.270%

    No Known Activations