© 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. 127977
    Prev
    Next
    INDEX
    Explanations

    non-English script or foreign terms

    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
     photographing
    -0.06
     kuj
    -0.06
    するなど
    -0.06
     decoração
    -0.06
     irgend
    -0.06
     Proses
    -0.06
     რომელიც
    -0.05
    র্শ
    -0.05
     halls
    -0.05
     처음
    -0.05
    POSITIVE LOGITS
     astonishing
    0.06
     touted
    0.06
     বিলম্ব
    0.06
     বৃদ্ধির
    0.06
    也许
    0.06
     साधा
    0.06
     ordinarily
    0.06
    essential
    0.06
    成分
    0.06
     essential
    0.06
    Activations Density 0.002%

    No Known Activations