© 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. 128725
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases and code snippets

    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
     chyba
    -0.07
     روز
    -0.06
    、
    -0.06
    名称
    -0.06
    लिंग
    -0.06
     filed
    -0.06
     也
    -0.05
    なくても
    -0.05
     önce
    -0.05
     riconosci
    -0.05
    POSITIVE LOGITS
     desperately
    0.07
     startups
    0.07
     whilst
    0.07
     সেই
    0.06
    svelte
    0.06
     if
    0.06
     infants
    0.06
    Neo
    0.06
    সেই
    0.06
     महत्त्वपूर्ण
    0.06
    Activations Density 0.009%

    No Known Activations