© 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. 118687
    Prev
    Next
    INDEX
    Explanations

    different possible numbers

    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
     abnormally
    -0.06
     важли
    -0.06
     Уже
    -0.06
     landmark
    -0.06
    지난
    -0.06
    iate
    -0.06
    melting
    -0.05
     candidats
    -0.05
     स्वभाव
    -0.05
    already
    -0.05
    POSITIVE LOGITS
     different
    0.08
     разных
    0.08
     različ
    0.07
     verschiedene
    0.07
     verschiedenen
    0.07
     verschillende
    0.07
    different
    0.07
     různých
    0.07
     aantal
    0.07
     różnych
    0.06
    Activations Density 0.023%

    No Known Activations