© 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. 130838
    Prev
    Next
    INDEX
    Explanations

    transport of substances

    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
     imagem
    -0.08
     image
    -0.07
     computation
    -0.07
     anticipation
    -0.07
    内核
    -0.07
    IRQ
    -0.06
    计算
    -0.06
     thoughts
    -0.06
    構造
    -0.06
     computing
    -0.06
    POSITIVE LOGITS
     transporters
    0.07
    に適
    0.07
    食べ
    0.07
    輸送
    0.06
    Eat
    0.06
    ڡ
    0.06
    afood
    0.06
     স্থানান্তর
    0.06
     intracellular
    0.06
     transport
    0.06
    Activations Density 0.025%

    No Known Activations