© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 116779
    Prev
    Next
    INDEX
    Explanations

    political bodies and offices

    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
     различные
    -0.08
     finer
    -0.07
     różne
    -0.07
     разные
    -0.06
     verschillende
    -0.06
     ডিভিশ
    -0.06
     різні
    -0.06
     sedan
    -0.06
     différentes
    -0.06
     पहिले
    -0.06
    POSITIVE LOGITS
    provide
    0.06
    年
    0.05
    uenza
    0.05
     बिल्
    0.05
    人で
    0.05
    recover
    0.05
    provides
    0.05
    Å
    0.05
    每一
    0.05
     año
    0.05
    Activations Density 0.012%

    No Known Activations