© 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. 120549
    Prev
    Next
    INDEX
    Explanations

    traditional or potentially

    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
     гораздо
    -0.07
    ;\
    -0.06
     forgiving
    -0.06
     something
    -0.06
     बिक्री
    -0.05
    something
    -0.05
     Visible
    -0.05
    ঙ্কে
    -0.05
    جموعة
    -0.05
     Something
    -0.05
    POSITIVE LOGITS
     traditionally
    0.08
     traditional
    0.07
    traditional
    0.07
     potentially
    0.07
    传统的
    0.07
    有可能
    0.07
     можуть
    0.07
    Traditionally
    0.06
     tradicion
    0.06
     Traditionally
    0.06
    Activations Density 0.009%

    No Known Activations