© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128166
    Prev
    Next
    INDEX
    Explanations

    terminal emulator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     three
    -0.06
     kilku
    -0.06
     drie
    -0.06
     trzech
    -0.06
     trzy
    -0.05
     trois
    -0.05
     নানান
    -0.05
     thậm
    -0.05
     several
    -0.05
     Verkauf
    -0.05
    POSITIVE LOGITS
    アクセス
    0.07
    作战
    0.06
     iletişim
    0.06
     勺
    0.06
     ⇒
    0.06
    研修
    0.06
    繡
    0.06
     فرهنگ
    0.06
    长
    0.06
     من
    0.06
    Activations Density 0.006%

    No Known Activations