© 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. 128540
    Prev
    Next
    INDEX
    Explanations

    protein structures and interactions

    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
     patented
    -0.08
     curr
    -0.06
     Retired
    -0.06
     esteemed
    -0.05
     acclaimed
    -0.05
     advertisements
    -0.05
     Temos
    -0.05
     Lees
    -0.05
     Parece
    -0.05
    absence
    -0.05
    POSITIVE LOGITS
     mao
    0.06
    𝚁
    0.06
    Primitives
    0.06
    내가
    0.06
    专辑
    0.06
    路上
    0.06
     insgesamt
    0.06
    后面
    0.06
     মোটামুটি
    0.06
     primitives
    0.06
    Activations Density 0.010%

    No Known Activations