© 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. 117097
    Prev
    Next
    INDEX
    Explanations

    endocytosis, lysosomes

    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
     Arabic
    -0.06
    无
    -0.06
     无
    -0.06
     знал
    -0.06
     выпу
    -0.06
     viens
    -0.06
     whimsical
    -0.06
     fueran
    -0.06
    کات
    -0.06
     quando
    -0.06
    POSITIVE LOGITS
     उपयुक्त
    0.06
     rome
    0.06
     multi
    0.06
    ดำเนินการ
    0.06
     arrears
    0.06
    כז
    0.06
     eigens
    0.06
     after
    0.06
     methods
    0.06
    imeters
    0.05
    Activations Density 0.002%

    No Known Activations