© 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. 118523
    Prev
    Next
    INDEX
    Explanations

    final favorite

    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
    一般
    -0.06
     réellement
    -0.06
     Özellikle
    -0.06
    被
    -0.06
    plify
    -0.06
     wichtig
    -0.06
     özellikle
    -0.06
    šu
    -0.06
     فقد
    -0.05
     generell
    -0.05
    POSITIVE LOGITS
     dialing
    0.06
     согласно
    0.06
     deres
    0.06
     предполага
    0.06
    một
    0.06
     någon
    0.06
    到
    0.06
     trastorno
    0.06
     disposable
    0.06
     sợi
    0.06
    Activations Density 0.002%

    No Known Activations