© 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. 115931
    Prev
    Next
    INDEX
    Explanations

    manufacturing goods

    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
     परिणामस्वरूप
    -0.07
     fair
    -0.06
    やはり
    -0.06
     travailler
    -0.06
     तानाशाह
    -0.05
    やる
    -0.05
    彼は
    -0.05
     finais
    -0.05
    стая
    -0.05
    料
    -0.05
    POSITIVE LOGITS
     মন্তব্য
    0.07
    取締
    0.06
     etik
    0.06
    忽略
    0.06
     সদস্য
    0.06
    checkbox
    0.06
    FLAGS
    0.06
     but
    0.06
     for
    0.06
     filmy
    0.06
    Activations Density 0.018%

    No Known Activations