© 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. 118079
    Prev
    Next
    INDEX
    Explanations

    constitutional, presidential, custom

    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
    Kitty
    -0.06
     følgende
    -0.06
     łącz
    -0.06
     नी
    -0.06
     csv
    -0.06
    医
    -0.06
     Brussels
    -0.06
     скорее
    -0.06
    iddish
    -0.06
    thymeleaf
    -0.06
    POSITIVE LOGITS
    カスタム
    0.06
     समायोजित
    0.06
    石油
    0.06
    Businessman
    0.06
     constitutional
    0.06
    ीडी
    0.05
     presidents
    0.05
    constitutional
    0.05
     properly
    0.05
     presidential
    0.05
    Activations Density 0.002%

    No Known Activations