© 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. 117592
    Prev
    Next
    INDEX
    Explanations

    type-1 diabetic

    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
     уют
    -0.06
     thậm
    -0.06
     smlou
    -0.06
     Notwithstanding
    -0.06
    記者
    -0.06
    atology
    -0.06
     databases
    -0.06
    mehr
    -0.06
     Porém
    -0.06
     다음과
    -0.06
    POSITIVE LOGITS
     departe
    0.06
     மத
    0.06
     livestock
    0.06
    MessageHandler
    0.05
     mixed
    0.05
     اكيد
    0.05
     daytime
    0.05
     giao
    0.05
     Prohibition
    0.05
    mixed
    0.05
    Activations Density 0.001%

    No Known Activations