© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115891
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "you", "i", or "q"

    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
     valuable
    -0.06
    ংস
    -0.06
     leisure
    -0.06
    与此同时
    -0.06
    兩人
    -0.06
     आपकी
    -0.05
    あなたは
    -0.05
    夫婦
    -0.05
    গল
    -0.05
    精彩
    -0.05
    POSITIVE LOGITS
     qualquer
    0.07
     любой
    0.07
     искать
    0.07
     any
    0.07
    任何
    0.07
     với
    0.07
     любую
    0.06
     ./
    0.06
     сейчас
    0.06
     другие
    0.06
    Activations Density 0.008%

    No Known Activations