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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130729
    Prev
    Next
    INDEX
    Explanations

    lactic acid, biodegradable polymers

    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
    焙
    -0.07
     distribuição
    -0.06
     tán
    -0.06
    散热
    -0.06
    虜
    -0.06
     Plenum
    -0.06
     получение
    -0.06
    ؟
    -0.06
    PX
    -0.06
     ایسی
    -0.06
    POSITIVE LOGITS
     designer
    0.07
     Designer
    0.06
     von
    0.06
     creator
    0.06
    inh
    0.06
    👛
    0.06
     genuinely
    0.06
     অ্যাকা
    0.06
     weaving
    0.06
     biome
    0.06
    Activations Density 0.008%

    No Known Activations