© 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. 117371
    Prev
    Next
    INDEX
    Explanations

    you are here

    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
     when
    -0.09
     When
    -0.08
     einer
    -0.08
    when
    -0.08
     когда
    -0.07
    When
    -0.07
     lorsque
    -0.07
     cuando
    -0.07
     một
    -0.07
     seria
    -0.07
    POSITIVE LOGITS
    これらの
    0.07
     inicialmente
    0.06
    ようになる
    0.06
     подобные
    0.06
    我们要
    0.06
    consistent
    0.06
    第一时间
    0.06
     नॉट
    0.06
     Mox
    0.05
     Vita
    0.05
    Activations Density 0.002%

    No Known Activations