© 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. 115841
    Prev
    Next
    INDEX
    Explanations

    muscles, tendons, and anatomical parts

    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
    最初は
    -0.06
    avik
    -0.06
     uner
    -0.06
    typicode
    -0.06
    उन्होंने
    -0.06
    ooq
    -0.06
     replicating
    -0.06
     explos
    -0.06
    iae
    -0.06
     tinker
    -0.06
    POSITIVE LOGITS
     cultures
    0.07
     உள்ளிட்ட
    0.06
     abiert
    0.06
     وأ
    0.06
     desses
    0.06
     послед
    0.06
     Cultures
    0.06
    Western
    0.06
    CUT
    0.06
     Descriptions
    0.06
    Activations Density 0.014%

    No Known Activations