© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130963
    Prev
    Next
    INDEX
    Explanations

    besides, special, legal protection

    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
     prenda
    -0.07
     Kalman
    -0.06
    agu
    -0.06
    otion
    -0.06
    வீன
    -0.06
     Command
    -0.06
     totality
    -0.05
     किमान
    -0.05
     удержи
    -0.05
    艺术
    -0.05
    POSITIVE LOGITS
     besides
    0.08
    besides
    0.07
     Besides
    0.07
     além
    0.07
     specials
    0.07
     selain
    0.07
     Ayrıca
    0.07
     special
    0.07
     ayrıca
    0.07
     spezielle
    0.07
    Activations Density 0.001%

    No Known Activations