© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 120893
    Prev
    Next
    INDEX
    Explanations

    segments or sequence items

    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
    Negative Logits
    개월
    -0.06
     absolutamente
    -0.06
    的一切
    -0.06
     सेटिंग
    -0.06
     一
    -0.06
     konusu
    -0.06
     dilakukan
    -0.06
     processes
    -0.06
     Should
    -0.06
     qualunque
    -0.06
    POSITIVE LOGITS
    উল্লেখ
    0.07
     réduire
    0.06
     otros
    0.06
    ണ്ടും
    0.06
     anderen
    0.06
    ないので
    0.06
    Weiter
    0.06
    så
    0.06
     outros
    0.06
     innych
    0.06
    Activations Density 0.001%

    No Known Activations