© 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. 118937
    Prev
    Next
    INDEX
    Explanations

    folding bed, Vietnam partridge

    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
    缕
    -0.06
     державних
    -0.06
     Adaptive
    -0.06
    Agricultural
    -0.06
    ほうが
    -0.06
     impatiently
    -0.06
     adaptive
    -0.06
    Adaptive
    -0.06
    adaptive
    -0.06
    richTextBox
    -0.06
    POSITIVE LOGITS
     sideline
    0.07
     возможности
    0.06
     възможно
    0.06
     dodat
    0.06
     einer
    0.06
     sidelines
    0.06
     fares
    0.06
    ヤ
    0.06
     mogelijkheden
    0.06
    ूँ
    0.06
    Activations Density 0.001%

    No Known Activations