© 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. 130205
    Prev
    Next
    INDEX
    Explanations

    Field of the Invention

    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
     ইত্যাদি
    -0.06
     방식
    -0.05
    supplied
    -0.05
    Understanding
    -0.05
     সবার
    -0.05
     Understanding
    -0.05
     australia
    -0.05
    *)
    -0.05
     first
    -0.05
    ড়াই
    -0.05
    POSITIVE LOGITS
     deviation
    0.07
     durchgeführt
    0.07
    كو
    0.07
     fiasco
    0.07
     esche
    0.07
     ছুটিতে
    0.06
     новую
    0.06
     Помимо
    0.06
    𝙇
    0.06
     तेंदुआ
    0.06
    Activations Density 0.002%

    No Known Activations