© 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. 120612
    Prev
    Next
    INDEX
    Explanations

    operating systems and platforms

    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
     among
    -0.06
     algunos
    -0.06
     два
    -0.06
     gọi
    -0.06
     இரண்டு
    -0.06
     trafi
    -0.06
    ｜
    -0.06
     ottenuto
    -0.06
     между
    -0.06
     two
    -0.06
    POSITIVE LOGITS
     прогно
    0.06
     lacking
    0.06
    Ibid
    0.06
    añ
    0.06
    텐
    0.06
    نان
    0.05
     still
    0.05
    페
    0.05
     functions
    0.05
    
    0.05
    Activations Density 0.001%

    No Known Activations