© 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. 131066
    Prev
    Next
    INDEX
    Explanations

    the right to

    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
     différentes
    -0.07
     diferentes
    -0.07
     different
    -0.07
     다양한
    -0.06
     distintos
    -0.06
     különböző
    -0.06
     possíveis
    -0.06
     we
    -0.06
     distintas
    -0.06
    different
    -0.06
    POSITIVE LOGITS
     들어가
    0.06
    নিতে
    0.06
     crisis
    0.06
     packet
    0.06
    Crisis
    0.06
     sorrows
    0.05
     नौकरी
    0.05
    crisis
    0.05
     सबसे
    0.05
     সম্ভবত
    0.05
    Activations Density 0.001%

    No Known Activations