© 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. 118653
    Prev
    Next
    INDEX
    Explanations

    numbers and ages, medical conditions

    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
     nelle
    -0.08
    ซึ่ง
    -0.07
     equipments
    -0.07
     চাষ
    -0.07
     boiler
    -0.07
     embarking
    -0.06
     reinvigor
    -0.06
     gigantic
    -0.06
     التي
    -0.06
     instituted
    -0.06
    POSITIVE LOGITS
    の
    0.06
    が
    0.06
    可以
    0.06
     зона
    0.05
     GUI
    0.05
    நிதி
    0.05
    resi
    0.05
    find
    0.05
    ghost
    0.05
    все
    0.05
    Activations Density 0.001%

    No Known Activations