© 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. 119468
    Prev
    Next
    INDEX
    Explanations

    district or electoral region

    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
     їх
    -0.07
     biggest
    -0.07
     largest
    -0.06
    largest
    -0.06
     kõige
    -0.06
    गु
    -0.06
     Their
    -0.06
    lerinde
    -0.06
     beslut
    -0.06
    lenie
    -0.05
    POSITIVE LOGITS
    彼の
    0.06
     издание
    0.06
     his
    0.06
     karat
    0.06
     securities
    0.06
     minced
    0.06
     필요한
    0.06
     सूर्या
    0.06
    彼は
    0.06
     আন্তর্জাতিক
    0.05
    Activations Density 0.022%

    No Known Activations