© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128633
    Prev
    Next
    INDEX
    Explanations

    war and conflict events

    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
     रस्त
    -0.06
     acceptable
    -0.06
     república
    -0.06
    一个
    -0.06
     verilen
    -0.06
    چال
    -0.06
    秪
    -0.06
    の
    -0.06
     শব্দ
    -0.05
     strtoupper
    -0.05
    POSITIVE LOGITS
    帮助
    0.07
    幫助
    0.06
    சரி
    0.06
    isolate
    0.06
     isolating
    0.06
     epiz
    0.06
     inflating
    0.06
     বক্ত
    0.06
    টা
    0.06
     kanyang
    0.06
    Activations Density 0.014%

    No Known Activations