© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130797
    Prev
    Next
    INDEX
    Explanations

    html tags and structure

    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
     Dlatego
    -0.06
     kalan
    -0.06
     Sosial
    -0.06
     wildly
    -0.06
     expansión
    -0.06
    archi
    -0.06
     英
    -0.05
     дохода
    -0.05
     excès
    -0.05
     copious
    -0.05
    POSITIVE LOGITS
     Dispersion
    0.07
     qui
    0.06
     সবকিছু
    0.06
     everything
    0.06
    everything
    0.06
     Metals
    0.06
    essment
    0.06
     খাওয়ার
    0.06
     Plastics
    0.06
     каждый
    0.05
    Activations Density 0.002%

    No Known Activations