© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119933
    Prev
    Next
    INDEX
    Explanations

    BB

    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
    ↵
    -2.86
    <em>
    -2.83
    俨
    -2.38
    ܞ
    -2.33
     sendo
    -2.33
    ANCE
    -2.27
    遢
    -2.27
    ☫
    -2.23
     is
    -2.23
    </u>
    -2.11
    POSITIVE LOGITS
    [
    3.16
    section
    2.94
    ons
    2.41
     suceder
    2.33
    กาย
    2.27
     Februar
    2.14
     захворювання
    2.06
    鱟
    2.06
     любить
    2.06
    ulihan
    2.05
    Activations Density 0.011%

    No Known Activations