© 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. 117635
    Prev
    Next
    INDEX
    Explanations

    domain names

    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
     similarities
    -0.06
     описание
    -0.06
     surgeons
    -0.06
     Douglas
    -0.06
     видео
    -0.06
     eros
    -0.06
     hedon
    -0.06
     বিকাশ
    -0.06
     эксплуатации
    -0.06
     longitudinal
    -0.06
    POSITIVE LOGITS
     ทำให้
    0.07
     recense
    0.06
     unbiased
    0.06
    干扰
    0.06
    तीने
    0.06
     باہر
    0.06
     allergic
    0.06
     lighthouse
    0.06
     Ascot
    0.06
     اوكي
    0.06
    Activations Density 0.002%

    No Known Activations