© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130798
    Prev
    Next
    INDEX
    Explanations

    various languages

    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
     Charles
    -0.06
     tweede
    -0.06
     charles
    -0.06
     дизайна
    -0.06
     Forschung
    -0.06
     시간
    -0.06
     Richard
    -0.06
     இரண்டாம்
    -0.06
     richard
    -0.06
     Khi
    -0.06
    POSITIVE LOGITS
     comme
    0.06
    يات
    0.06
     như
    0.06
     ফেলেছে
    0.06
     como
    0.05
     procura
    0.05
     он
    0.05
     dei
    0.05
     extends
    0.05
    לי
    0.05
    Activations Density 0.007%

    No Known Activations