© 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. 117252
    Prev
    Next
    INDEX
    Explanations

    body fluids, disease, health, models

    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
    :
    -0.07
     in
    -0.06
    Sand
    -0.06
    พื้น
    -0.06
     использова
    -0.06
     আরম্ভ
    -0.06
     χρησιμοποι
    -0.06
     при
    -0.06
     ingress
    -0.06
     sand
    -0.06
    POSITIVE LOGITS
     نفسي
    0.06
    ╁
    0.06
     dopp
    0.06
     consultants
    0.06
     mentre
    0.06
    자를
    0.06
     نفسك
    0.06
    包括
    0.06
     sondern
    0.06
     sẽ
    0.06
    Activations Density 0.024%

    No Known Activations