© 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. 117264
    Prev
    Next
    INDEX
    Explanations

    code comments and declarations

    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
     খুব
    -0.07
     বেশ
    -0.06
     لأن
    -0.06
     если
    -0.06
    mateurs
    -0.06
     अपेक्षाकृत
    -0.06
     very
    -0.06
    भावना
    -0.06
     اگر
    -0.06
     لأنه
    -0.06
    POSITIVE LOGITS
     in
    0.07
     by
    0.07
     Chúng
    0.07
    Trong
    0.06
     Musik
    0.06
    ươ
    0.06
     nuovi
    0.06
     chúng
    0.06
     phiếu
    0.06
    annt
    0.06
    Activations Density 0.001%

    No Known Activations