© 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. 120856
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
    送料無料
    -0.06
     mengatakan
    -0.06
     ranging
    -0.06
     számos
    -0.06
     Eles
    -0.06
     Điều
    -0.06
    OrCreate
    -0.06
     Soccer
    -0.06
     esclare
    -0.06
     mevcut
    -0.06
    POSITIVE LOGITS
     밑
    0.06
     only
    0.06
     τόσο
    0.06
    曇
    0.06
     was
    0.06
     both
    0.06
     had
    0.06
     would
    0.06
    ርድ
    0.06
     შემ
    0.06
    Activations Density 0.002%

    No Known Activations