© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128603
    Prev
    Next
    INDEX
    Explanations

    broadcasting and streaming

    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
     itself
    -0.07
     withstand
    -0.07
    Gonz
    -0.06
     rodi
    -0.06
     гне
    -0.06
     пър
    -0.06
     doma
    -0.06
     Andrews
    -0.06
    film
    -0.06
     withstood
    -0.06
    POSITIVE LOGITS
     técn
    0.06
     auswählen
    0.06
     Bag
    0.06
    过后
    0.06
    各
    0.06
     প্রচার
    0.06
    内在
    0.05
     பெய
    0.05
     tecn
    0.05
     relevante
    0.05
    Activations Density 0.003%

    No Known Activations