© 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. 130765
    Prev
    Next
    INDEX
    Explanations

    see also

    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
     the
    -0.09
     ketika
    -0.07
     fhe
    -0.07
    もしくは
    -0.07
    Когда
    -0.07
     stipulated
    -0.07
     inspired
    -0.07
     esimerkiksi
    -0.07
     increasingly
    -0.07
     more
    -0.07
    POSITIVE LOGITS
     above
    0.08
     ऊपर
    0.08
     yukarı
    0.07
     ઉપર
    0.06
    above
    0.06
     arriba
    0.06
     위의
    0.06
    。
    0.06
    XIII
    0.06
    )。
    0.06
    Activations Density 0.003%

    No Known Activations