© 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. 119862
    Prev
    Next
    INDEX
    Explanations

    USLW

    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
     quick
    -0.08
    quick
    -0.08
    یە
    -0.07
     चिंत
    -0.06
    Quick
    -0.06
    ⚖
    -0.06
     leur
    -0.06
     Quick
    -0.06
     QUICK
    -0.06
    ede
    -0.06
    POSITIVE LOGITS
     vielfält
    0.07
     различными
    0.07
    ских
    0.06
     autrefois
    0.06
    ધન
    0.06
    બા
    0.06
    八
    0.06
     самых
    0.06
    ского
    0.06
     современных
    0.06
    Activations Density 0.002%

    No Known Activations