© 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. 127974
    Prev
    Next
    INDEX
    Explanations

    code comments and sections

    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
     결과
    -0.07
    ۸
    -0.07
    結果
    -0.06
     geralmente
    -0.06
    或者
    -0.06
    有时候
    -0.06
     иногда
    -0.06
     atau
    -0.06
     czasem
    -0.06
     이런
    -0.06
    POSITIVE LOGITS
     newly
    0.06
    дың
    0.06
     proposed
    0.06
     Muff
    0.06
     terse
    0.06
     प्रस्तावित
    0.06
    Está
    0.06
    azionale
    0.06
     New
    0.06
     troublesome
    0.05
    Activations Density 0.003%

    No Known Activations