© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117734
    Prev
    Next
    INDEX
    Explanations

    appearances

    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
    !!!
    -0.06
    像
    -0.06
     👉
    -0.06
    جام
    -0.06
    !!
    -0.06
    👉
    -0.06
     படத்தில்
    -0.06
    🍄
    -0.06
    !!!!
    -0.06
     सेक्टर
    -0.06
    POSITIVE LOGITS
    کل
    0.07
     moderately
    0.06
    伍
    0.06
     is
    0.06
     사용하는
    0.06
    認為
    0.06
     nieruch
    0.06
     tipo
    0.06
     particolarmente
    0.06
    嶅
    0.06
    Activations Density 0.013%

    No Known Activations