© 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. 129123
    Prev
    Next
    INDEX
    Explanations

    HTML structure and multiligual text

    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
    same
    -0.06
     unab
    -0.06
    smaller
    -0.06
     exceptionnelle
    -0.06
     GAS
    -0.06
     onderzoek
    -0.06
     বেড়েছে
    -0.06
     campaigners
    -0.06
     ಸ್ಥಳ
    -0.06
     repetition
    -0.06
    POSITIVE LOGITS
    将其
    0.06
     никакого
    0.06
    जिंग
    0.05
     ialah
    0.05
     نمی
    0.05
    になって
    0.05
     sont
    0.05
    互相
    0.05
     gelang
    0.05
    to
    0.05
    Activations Density 0.002%

    No Known Activations