© 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. 117248
    Prev
    Next
    INDEX
    Explanations

    Plaintiff after punctuation

    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
     برخی
    -0.07
     если
    -0.06
     بعض
    -0.06
     }}(\
    -0.06
    Kas
    -0.06
     вули
    -0.06
     henüz
    -0.06
     symbolically
    -0.06
    कुछ
    -0.06
     ಕೆಲವು
    -0.06
    POSITIVE LOGITS
     now
    0.08
    -
    0.06
     analysed
    0.06
     יכול
    0.06
     respectively
    0.06
     intending
    0.06
    観察
    0.06
    อื่น
    0.06
     consulted
    0.06
     ihtiy
    0.06
    Activations Density 0.014%

    No Known Activations