© 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. 119076
    Prev
    Next
    INDEX
    Explanations

    return Json

    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
     महंगा
    -0.05
     Renato
    -0.05
    URATION
    -0.05
     दिवशी
    -0.05
     boolean
    -0.05
    、
    -0.05
    erer
    -0.05
     ///
    -0.05
    बताया
    -0.05
     যশোরে
    -0.05
    POSITIVE LOGITS
    Cuando
    0.08
     उसे
    0.07
     inaug
    0.07
     Cuando
    0.07
     தருக
    0.06
     può
    0.06
     its
    0.06
     sizi
    0.06
     the
    0.06
     Dienstag
    0.06
    Activations Density 0.001%

    No Known Activations