© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129366
    Prev
    Next
    INDEX
    Explanations

    Pan-American Treaty, Introduction, specific objectives

    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
     নীতির
    -0.06
    ǎ
    -0.06
     рекомендации
    -0.06
     ফর্ম
    -0.06
     হিসাবে
    -0.06
     পদ্ধতি
    -0.06
     pilihan
    -0.05
     ການ
    -0.05
     compartir
    -0.05
     sharing
    -0.05
    POSITIVE LOGITS
     suspicious
    0.07
     suspicions
    0.07
     reservoirs
    0.06
     scheming
    0.06
    Objectives
    0.06
     serene
    0.06
     suspicion
    0.06
     suspect
    0.06
    ênio
    0.06
     suspected
    0.06
    Activations Density 0.003%

    No Known Activations