© 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. 130772
    Prev
    Next
    INDEX
    Explanations

    statistics involving numbers and units

    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
     최대한
    -0.07
     නව
    -0.06
     entire
    -0.06
     cały
    -0.06
     researches
    -0.06
     możliwe
    -0.06
     lifestyles
    -0.06
     বিশ্বাস
    -0.06
     повністю
    -0.06
     totalmente
    -0.06
    POSITIVE LOGITS
    បញ្ចូល
    0.06
     these
    0.06
    iply
    0.06
     መጨ
    0.06
     artillery
    0.06
     इन
    0.06
     ನಾವು
    0.05
    这两
    0.05
    潮
    0.05
    danger
    0.05
    Activations Density 0.011%

    No Known Activations