© 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. 129104
    Prev
    Next
    INDEX
    Explanations

    mechanical devices and systems

    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
     получения
    -0.07
     that
    -0.07
     gyro
    -0.06
     प्रतिदिन
    -0.06
     পশ্চিম
    -0.06
     रिवाज
    -0.06
     час
    -0.06
     выну
    -0.06
    アクセサリー
    -0.06
     Григо
    -0.06
    POSITIVE LOGITS
     delineate
    0.06
     Specialty
    0.06
     strategically
    0.06
    ⌇
    0.06
     yet
    0.06
     Lacy
    0.06
     Strateg
    0.06
    sql
    0.06
    irdiği
    0.06
     있고요
    0.05
    Activations Density 0.025%

    No Known Activations