© 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. 118618
    Prev
    Next
    INDEX
    Explanations

    technical topics and programming

    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
     മറ്റൊരു
    -0.06
     मुकाबले
    -0.06
    疠
    -0.06
     কখনো
    -0.06
     geliyor
    -0.06
     entsteht
    -0.06
     আস্তে
    -0.06
    取代
    -0.06
     небе
    -0.06
    sulf
    -0.05
    POSITIVE LOGITS
     ন্যায
    0.07
    really
    0.06
     vraiment
    0.06
     первый
    0.06
     परिवर्त
    0.06
     കൂടുത
    0.06
    changes
    0.06
     melalui
    0.06
     boolean
    0.06
    ясь
    0.06
    Activations Density 0.027%

    No Known Activations