© 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. 120020
    Prev
    Next
    INDEX
    Explanations

    enable strict matching

    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
     begins
    -0.06
     all
    -0.06
    需要
    -0.06
     nabíz
    -0.06
     এখনও
    -0.06
     gerekiyor
    -0.06
     need
    -0.06
    まずは
    -0.06
     আসলে
    -0.06
     প্রয়োজন
    -0.06
    POSITIVE LOGITS
     örnek
    0.07
     формування
    0.06
     їх
    0.06
    
    0.06
    Arvore
    0.06
     Tipps
    0.06
     দিতেন
    0.06
    pción
    0.06
     aquí
    0.06
    roits
    0.06
    Activations Density 0.001%

    No Known Activations