© 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. 116616
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and quantities

    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
     boasts
    -0.06
     的
    -0.06
     の
    -0.06
     única
    -0.06
     金
    -0.06
     arrangement
    -0.06
     added
    -0.06
     único
    -0.06
    只有一个
    -0.06
    的那
    -0.06
    POSITIVE LOGITS
     these
    0.08
    เหล่านี้
    0.07
    這些
    0.07
     estos
    0.07
    这些
    0.07
    これらの
    0.06
    these
    0.06
     éstas
    0.06
     bunları
    0.06
     これらの
    0.06
    Activations Density 0.003%

    No Known Activations