© 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. 116642
    Prev
    Next
    INDEX
    Explanations

    differentially expressed genes

    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
     tuttavia
    -0.07
    龙
    -0.07
     известен
    -0.06
    ﯿ
    -0.06
     جهانی
    -0.06
     لیکن
    -0.06
     bizony
    -0.06
     explorar
    -0.06
    調査
    -0.06
     consegue
    -0.06
    POSITIVE LOGITS
     Particularly
    0.06
    感兴趣
    0.06
     specifically
    0.06
     cầm
    0.06
     Bereich
    0.06
     это
    0.06
     ایسا
    0.06
     مراسم
    0.06
    particularly
    0.06
     particularmente
    0.06
    Activations Density 0.025%

    No Known Activations