© 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. 117361
    Prev
    Next
    INDEX
    Explanations

    degrees or meters

    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
     ১৬
    -0.06
     sucesso
    -0.06
    yeah
    -0.06
     misfortunes
    -0.06
     ohne
    -0.06
     criticisms
    -0.06
     নিত্য
    -0.06
    真是
    -0.06
     ક
    -0.06
     cien
    -0.06
    POSITIVE LOGITS
    breast
    0.06
     Those
    0.06
     طریق
    0.06
     recommend
    0.06
     those
    0.05
     apag
    0.05
    นั้น
    0.05
    ª
    0.05
    女優
    0.05
    বাংলাদেশে
    0.05
    Activations Density 0.001%

    No Known Activations