© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130876
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania

    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
     usually
    -0.08
    aprendizaje
    -0.07
     zawsze
    -0.06
     এটির
    -0.06
     always
    -0.06
     tremendously
    -0.06
     typically
    -0.06
    usually
    -0.06
     অসংখ্য
    -0.06
     सोचने
    -0.06
    POSITIVE LOGITS
     homemade
    0.06
     an
    0.06
     Homemade
    0.06
     IN
    0.06
     recent
    0.06
     add
    0.06
    льные
    0.06
     необходимые
    0.05
     Artisan
    0.05
    malı
    0.05
    Activations Density 0.003%

    No Known Activations