© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117528
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes

    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
    任何
    -0.07
     milyon
    -0.07
     millions
    -0.06
     celui
    -0.06
     has
    -0.06
     టి
    -0.06
     Puede
    -0.06
    前記
    -0.06
     When
    -0.06
     Without
    -0.06
    POSITIVE LOGITS
     vergangenen
    0.06
     моя
    0.06
     fashioned
    0.06
    Voilà
    0.06
    uxx
    0.06
     οικονομ
    0.06
    更新
    0.05
    이라는
    0.05
     निर्णय
    0.05
    ZIONE
    0.05
    Activations Density 0.006%

    No Known Activations