© 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. 128138
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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
     Date
    -0.06
    邯
    -0.06
     nanoc
    -0.06
     중
    -0.06
    ：
    -0.06
     importante
    -0.06
     quase
    -0.06
     cũng
    -0.06
     však
    -0.06
     porém
    -0.06
    POSITIVE LOGITS
     njih
    0.06
     their
    0.06
     triad
    0.06
     (!)
    0.06
     아무
    0.06
    implantation
    0.06
    izieren
    0.06
    łą
    0.06
    (!)
    0.06
    ,.
    0.05
    Activations Density 0.007%

    No Known Activations