© 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. 58878
    Prev
    Next
    INDEX
    Explanations

    quotes and code snippets

    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
    们的
    -2.59
    是想
    -2.48
    鄖
    -2.34
     Begleitung
    -2.33
    ～。
    -2.30
    zość
    -2.30
    那我
    -2.27
    ovať
    -2.23
     ,‬
    -2.22
     člov
    -2.20
    POSITIVE LOGITS
    *
    3.27
    e
    3.23
    栳
    3.11
    <
    2.83
    "\
    2.69
    𝐒
    2.67
    [
    2.38
    ка
    2.34
    <0xEC>
    2.33
    ܃
    2.30
    Activations Density 0.001%

    No Known Activations