© 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. 119600
    Prev
    Next
    INDEX
    Explanations

    malaria parasites

    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
     worldwide
    -0.08
    worldwide
    -0.08
     global
    -0.07
    全球
    -0.07
     глоба
    -0.07
     belum
    -0.07
    全局
    -0.07
     다섯
    -0.07
     five
    -0.07
    海外
    -0.07
    POSITIVE LOGITS
     any
    0.06
     kid
    0.06
     kids
    0.06
     genç
    0.06
     kiddos
    0.06
     Millennials
    0.05
    пре
    0.05
     valid
    0.05
    恩
    0.05
     обнаружи
    0.05
    Activations Density 0.005%

    No Known Activations