© 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. 120480
    Prev
    Next
    INDEX
    Explanations

    days before the week

    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
     ample
    -0.06
     voor
    -0.06
     requisite
    -0.06
     व्यापक
    -0.06
     特
    -0.06
     louder
    -0.06
     amplio
    -0.05
     amplia
    -0.05
    init
    -0.05
     カ
    -0.05
    POSITIVE LOGITS
     სისტ
    0.06
     эти
    0.06
     ছিলাম
    0.06
    ここでは
    0.06
    これ
    0.06
    これにより
    0.06
     někter
    0.06
     đây
    0.06
     Certaines
    0.06
    這些
    0.06
    Activations Density 0.010%

    No Known Activations