© 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. 116043
    Prev
    Next
    INDEX
    Explanations

    numbers and calculation operators

    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
     కొత్త
    -0.07
    今回の
    -0.07
     지금
    -0.07
    男子
    -0.06
     например
    -0.06
     নতুন
    -0.06
     Maximal
    -0.06
    鍙
    -0.06
     ಇದ
    -0.06
     cappuccino
    -0.06
    POSITIVE LOGITS
     four
    0.06
     små
    0.06
     oo
    0.06
     minuscule
    0.06
     three
    0.05
    遲
    0.05
     refuse
    0.05
     tiny
    0.05
    小さな
    0.05
     membangun
    0.05
    Activations Density 0.003%

    No Known Activations