© 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. 116121
    Prev
    Next
    INDEX
    Explanations

    numbers proceeding articles or chapters

    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
     pomeriggio
    -0.06
     prioritizing
    -0.05
     dette
    -0.05
    ),
    -0.05
     половины
    -0.05
     éton
    -0.05
    ruvate
    -0.05
     consummate
    -0.05
     einschließlich
    -0.05
    see
    -0.05
    POSITIVE LOGITS
     सामान्य
    0.08
     अन्य
    0.07
     diğer
    0.07
     Porém
    0.07
     però
    0.07
     সাধারণ
    0.06
    ยัง
    0.06
    তবে
    0.06
     typical
    0.06
     ただ
    0.06
    Activations Density 0.001%

    No Known Activations