© 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. 130948
    Prev
    Next
    INDEX
    Explanations

    different or various

    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
     可以
    -0.07
     that
    -0.07
     حتى
    -0.07
     прият
    -0.07
     потому
    -0.07
     enough
    -0.07
     until
    -0.07
    までは
    -0.06
     genug
    -0.06
     for
    -0.06
    POSITIVE LOGITS
     अलग
    0.09
     diferentes
    0.09
     forskjellige
    0.08
     różnych
    0.08
     different
    0.08
     verschiedenen
    0.08
     verschillende
    0.08
     различных
    0.08
     مختلف
    0.08
     various
    0.08
    Activations Density 0.157%

    No Known Activations