© 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. 117389
    Prev
    Next
    INDEX
    Explanations

    commentary on social media, website, SEO

    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
    快速
    -0.06
     schnell
    -0.06
    更快
    -0.06
     fastest
    -0.06
     schneller
    -0.06
     nhanh
    -0.06
     అనేది
    -0.06
     rewards
    -0.06
     funziona
    -0.06
     faster
    -0.06
    POSITIVE LOGITS
    組み合わせ
    0.07
     Facebook
    0.07
    打电话
    0.06
    Facebook
    0.06
    Complete
    0.06
     facebook
    0.06
     spéciaux
    0.06
     telepon
    0.06
     aband
    0.06
     provincial
    0.06
    Activations Density 0.023%

    No Known Activations