© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120312
    Prev
    Next
    INDEX
    Explanations

    development and testing

    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
    没有什么
    -0.06
    방법
    -0.06
     personnes
    -0.06
     cinqu
    -0.06
     различни
    -0.06
     principalement
    -0.06
    新たな
    -0.06
     distintos
    -0.06
    Employ
    -0.06
     কাঁদতে
    -0.06
    POSITIVE LOGITS
     طراحی
    0.07
    design
    0.06
     साजिश
    0.06
    设计
    0.06
    设计的
    0.06
    Deviation
    0.06
    veget
    0.05
     faz
    0.05
     veget
    0.05
     during
    0.05
    Activations Density 0.086%

    No Known Activations