© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117339
    Prev
    Next
    INDEX
    Explanations

    glycosylated hemoglobin (HbA1c) analysis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     பெரிய
    -0.06
     hours
    -0.06
     Bucure
    -0.06
     HDPE
    -0.06
     impromptu
    -0.06
     ځای
    -0.06
    large
    -0.06
     नया
    -0.06
    já
    -0.06
    missing
    -0.06
    POSITIVE LOGITS
    Brasil
    0.07
    Months
    0.06
     Racism
    0.06
    半年
    0.06
     месяц
    0.06
     brazil
    0.06
    自転車
    0.06
     ಇಂಡ
    0.06
     month
    0.06
     ”.
    0.06
    Activations Density 0.004%

    No Known Activations