© 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. 129268
    Prev
    Next
    INDEX
    Explanations

    sql query statement

    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
     lawsuit
    -0.06
     filepath
    -0.06
    ೆ
    -0.06
     ಔಷಧ
    -0.06
    Swift
    -0.06
     WK
    -0.06
     당시
    -0.06
    ایه
    -0.06
    Latitude
    -0.06
     ఇంటి
    -0.06
    POSITIVE LOGITS
    Collector
    0.07
    是不是
    0.06
    เร
    0.06
    σό
    0.06
    是
    0.06
     collector
    0.06
    InnoDB
    0.05
     trưởng
    0.05
    XXX
    0.05
    唷
    0.05
    Activations Density 0.010%

    No Known Activations