© 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. 128262
    Prev
    Next
    INDEX
    Explanations

    Eclipse Public License

    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
    我觉得
    -0.06
    某个
    -0.06
     jednu
    -0.06
    etro
    -0.06
     overarching
    -0.06
     specific
    -0.06
     holographic
    -0.06
    すごく
    -0.06
    ەکانی
    -0.06
     adalah
    -0.06
    POSITIVE LOGITS
    有無
    0.06
     partir
    0.06
    will
    0.06
     meagre
    0.06
     will
    0.06
    嗎
    0.06
     prawdopod
    0.06
     sẽ
    0.05
    youtu
    0.05
     наличи
    0.05
    Activations Density 0.002%

    No Known Activations