© 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. 116086
    Prev
    Next
    INDEX
    Explanations

    dates and metadata separators

    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
    小小
    -0.06
    如果
    -0.06
    ξη
    -0.06
    忘记
    -0.06
     jika
    -0.06
     மறந்து
    -0.06
     작은
    -0.06
     مثال
    -0.06
     якщо
    -0.06
     забы
    -0.06
    POSITIVE LOGITS
     from
    0.07
     যেদিন
    0.07
     aspect
    0.06
    Either
    0.06
     notable
    0.06
    female
    0.06
    Aspect
    0.06
    大约
    0.06
     Approximately
    0.06
     während
    0.06
    Activations Density 0.007%

    No Known Activations