© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111561
    Prev
    Next
    INDEX
    Explanations

    grew up

    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
     get
    -1.37
     if
    -1.23
     or
    -1.23
    够了
    -1.23
     then
    -1.20
    abilirsiniz
    -1.20
     remain
    -1.17
     send
    -1.16
     continue
    -1.16
     back
    -1.11
    POSITIVE LOGITS
     ทั้ง
    1.29
     zarówno
    1.28
    色んな
    1.28
     ใน
    1.28
     Estas
    1.26
    (/[
    1.26
     négociations
    1.24
     приготовить
    1.20
    まさか
    1.20
     gainera
    1.20
    Activations Density 0.034%

    No Known Activations