© 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. 128821
    Prev
    Next
    INDEX
    Explanations

    plugin, tool, or library names

    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
     relação
    -0.07
     sürec
    -0.07
     puis
    -0.06
    ).
    -0.06
     UIColor
    -0.06
     seiner
    -0.06
    ）.
    -0.06
     color
    -0.06
     colore
    -0.06
    、
    -0.06
    POSITIVE LOGITS
     लगातार
    0.07
    START
    0.06
     ऊपरी
    0.06
     oleh
    0.06
     বিভিন্ন
    0.06
    大部分
    0.06
    部份
    0.06
     thinkers
    0.06
    अंत
    0.06
    続ける
    0.06
    Activations Density 0.001%

    No Known Activations