© 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. 118651
    Prev
    Next
    INDEX
    Explanations

    multicast and broadcast communication

    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
     kuwa
    -0.06
     isolates
    -0.06
    ünst
    -0.05
    持续
    -0.05
    Kamu
    -0.05
     Governments
    -0.05
    不断
    -0.05
     tribunals
    -0.05
    whose
    -0.05
    🦓
    -0.05
    POSITIVE LOGITS
     petición
    0.06
     تعمیر
    0.06
     descrizione
    0.06
     descripción
    0.06
     মেরামত
    0.06
     возле
    0.06
    দেখে
    0.06
    UNLOCK
    0.06
     localización
    0.06
     localização
    0.06
    Activations Density 0.002%

    No Known Activations