© 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. 119627
    Prev
    Next
    INDEX
    Explanations

    configuration files

    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
    比如
    -0.07
     مثلا
    -0.07
    ;
    -0.07
    Neighbor
    -0.07
     beispielsweise
    -0.07
     culoare
    -0.07
     bijvoorbeeld
    -0.06
     yakni
    -0.06
     โดย
    -0.06
     например
    -0.06
    POSITIVE LOGITS
     zijn
    0.07
     বিভিন্ন
    0.06
     also
    0.06
    ↵
    0.06
     journalist
    0.06
    様々な
    0.05
     आखिरकार
    0.05
     여러
    0.05
     גם
    0.05
     जरूर
    0.05
    Activations Density 0.001%

    No Known Activations