© 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. 118427
    Prev
    Next
    INDEX
    Explanations

    either a distinct

    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
     দায়িত্বে
    -0.06
     removing
    -0.06
     between
    -0.06
     Frente
    -0.06
     frente
    -0.06
     마찬가지
    -0.06
    Between
    -0.06
    again
    -0.06
     Removing
    -0.06
     mengenai
    -0.05
    POSITIVE LOGITS
     прежде
    0.07
     destinados
    0.07
     destinado
    0.07
     dependiendo
    0.07
    尽快
    0.07
     destinés
    0.07
    这就是
    0.06
    typical
    0.06
     kinds
    0.06
    走向
    0.06
    Activations Density 0.031%

    No Known Activations