© 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. 117188
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and specific words like Spain

    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
     ನಂತರ
    -0.06
     brachial
    -0.06
     показать
    -0.06
     a
    -0.06
    那就是
    -0.05
     seven
    -0.05
     सप्त
    -0.05
    。
    -0.05
     Selanjutnya
    -0.05
     दिवशी
    -0.05
    POSITIVE LOGITS
    Regardless
    0.06
     ყველ
    0.06
     ಇದಕ್ಕೆ
    0.06
     irrespective
    0.06
     ছেলেদের
    0.06
     ʻ
    0.06
     übrigens
    0.06
     Edit
    0.06
    Angelo
    0.06
     regardless
    0.06
    Activations Density 0.001%

    No Known Activations