© 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. 129970
    Prev
    Next
    INDEX
    Explanations

    metadata keys

    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
     legitimate
    -0.06
    จริงๆ
    -0.06
     specific
    -0.06
     মুক্তিযুদ্ধ
    -0.05
     بالفعل
    -0.05
     fie
    -0.05
    specific
    -0.05
    😺
    -0.05
     Jur
    -0.05
     gsub
    -0.05
    POSITIVE LOGITS
     அனைத்து
    0.07
     всіх
    0.07
     کامل
    0.07
     ಎಲ್ಲಾ
    0.07
     완전
    0.07
     tutta
    0.07
     מלא
    0.06
     ملي
    0.06
     voor
    0.06
     karena
    0.06
    Activations Density 0.003%

    No Known Activations