© 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. 119737
    Prev
    Next
    INDEX
    Explanations

    database tables

    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
     विरासत
    -0.07
     anon
    -0.07
     इन
    -0.06
     Química
    -0.06
    failure
    -0.06
     гало
    -0.06
     آن‌ها
    -0.06
    iminary
    -0.06
     Whatever
    -0.06
    larını
    -0.06
    POSITIVE LOGITS
     आसान
    0.06
     därför
    0.06
     一个
    0.06
    bouw
    0.06
     хозя
    0.06
     wealthy
    0.06
     मंत्री
    0.05
     челове
    0.05
     therefore
    0.05
     donc
    0.05
    Activations Density 0.049%

    No Known Activations