© 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. 58966
    Prev
    Next
    INDEX
    Explanations

    clonidine, brevis, Luoluopo, olefin, Ndong, ben, electrum, Coggon, Grigsby, Pereskia, chipolata, Stylonurella

    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
     the
    -1.75
    ing
    -1.54
     recientes
    -1.20
     boeken
    -1.16
     {;
    -1.09
     べ
    -1.09
     による
    -1.08
    zad
    -1.07
     by
    -1.05
     İl
    -1.05
    POSITIVE LOGITS
    顧客
    1.33
     then
    1.32
    　　「
    1.24
    缺點
    1.22
    錚
    1.20
     інші
    1.18
    兩個
    1.17
    然後
    1.16
     různ
    1.16
    英語版
    1.15
    Activations Density 0.134%

    No Known Activations