© 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. 130574
    Prev
    Next
    INDEX
    Explanations

    demands UN respect missile

    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
    不斷
    -0.07
     menghasilkan
    -0.06
    不断
    -0.06
    も
    -0.06
    CreationFailed
    -0.06
    Strategy
    -0.06
    が
    -0.06
    
    -0.06
     Strategy
    -0.06
     खुद
    -0.06
    POSITIVE LOGITS
     zgod
    0.06
     compartilhar
    0.06
    iş
    0.06
     coincid
    0.06
     दोघा
    0.06
     agreed
    0.06
    くらい
    0.06
     agrees
    0.06
     mutually
    0.06
     You
    0.06
    Activations Density 0.011%

    No Known Activations