© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118455
    Prev
    Next
    INDEX
    Explanations

    physical states or components

    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
     to
    -0.07
    这
    -0.07
    という
    -0.07
    這
    -0.07
    သောအ
    -0.06
    라는
    -0.06
     riêng
    -0.06
     чего
    -0.06
    そういう
    -0.06
     Ve
    -0.06
    POSITIVE LOGITS
     extremely
    0.06
    ˆ‚
    0.06
     achieved
    0.06
     หาก
    0.06
    ्यानंतर
    0.06
    直至
    0.06
    直到
    0.06
     ඔවුන්
    0.06
     ensure
    0.06
     온라인
    0.06
    Activations Density 0.016%

    No Known Activations