© 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. 129340
    Prev
    Next
    INDEX
    Explanations

    id identifiers

    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
     poolside
    -0.07
    routes
    -0.06
    Acces
    -0.06
     enemies
    -0.06
     vital
    -0.06
    ząd
    -0.06
     eBay
    -0.06
     ebay
    -0.06
     guided
    -0.06
     mainstay
    -0.06
    POSITIVE LOGITS
    \\\\
    0.06
    льных
    0.06
              
    0.06
          
    0.06
     chois
    0.06
    ưng
    0.06
     policía
    0.06
    requent
    0.06
    abilecek
    0.05
     आवेदक
    0.05
    Activations Density 0.003%

    No Known Activations