© 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. 129705
    Prev
    Next
    INDEX
    Explanations

    ingredients and proper nouns

    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
     first
    -0.08
     menunggu
    -0.08
     chờ
    -0.07
     먼저
    -0.07
     pierwszej
    -0.07
    TIME
    -0.07
     waiting
    -0.06
     esperar
    -0.06
     time
    -0.06
     waits
    -0.06
    POSITIVE LOGITS
     প্রকাশ
    0.06
    क्चर
    0.06
     jezik
    0.06
    Тем
    0.06
    лете
    0.06
     messaggio
    0.06
     unravel
    0.06
     amulet
    0.06
     mensagem
    0.05
    ōu
    0.05
    Activations Density 0.004%

    No Known Activations