© 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. 128073
    Prev
    Next
    INDEX
    Explanations

    used for preparing

    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
     этом
    -0.07
    ILLA
    -0.06
     প্রবল
    -0.06
    ⏪
    -0.06
     divisional
    -0.06
     открытия
    -0.06
     deinen
    -0.06
     सड़कों
    -0.06
     বিশ্লে
    -0.06
    大全
    -0.06
    POSITIVE LOGITS
     তাদেরকে
    0.06
    五
    0.06
    6
    0.06
    那位
    0.06
     একজন
    0.05
    1
    0.05
    自己
    0.05
     जिक्र
    0.05
     Pty
    0.05
    7
    0.05
    Activations Density 0.020%

    No Known Activations