© 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. 130261
    Prev
    Next
    INDEX
    Explanations

    questions and cases

    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
     political
    -0.07
     .......
    -0.06
     activism
    -0.06
    印象
    -0.06
     vote
    -0.06
     Political
    -0.06
     politically
    -0.06
    Political
    -0.06
    政治
    -0.06
     রাজনী
    -0.06
    POSITIVE LOGITS
     ज़रूरी
    0.07
     sürekli
    0.06
     continually
    0.06
     अजीब
    0.06
    Después
    0.06
     계속
    0.06
     patients
    0.06
    神奇
    0.06
     gerekli
    0.06
     strange
    0.06
    Activations Density 0.012%

    No Known Activations