© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130255
    Prev
    Next
    INDEX
    Explanations

    electric and electrostatic fields

    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
    륨
    -0.07
     politician
    -0.06
     політи
    -0.06
    axa
    -0.06
     জনসাধারণ
    -0.06
     electrol
    -0.06
     political
    -0.06
     रणनीति
    -0.06
    ষ্কৃত
    -0.06
     PKK
    -0.06
    POSITIVE LOGITS
    初の
    0.07
     direkt
    0.06
    著名的
    0.06
     trực
    0.06
    CON
    0.06
    ationale
    0.06
     DIRECT
    0.06
     staged
    0.06
    first
    0.06
    等等
    0.06
    Activations Density 0.004%

    No Known Activations