© 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. 118708
    Prev
    Next
    INDEX
    Explanations

    British and French history

    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
    エコ
    -0.06
    interpol
    -0.06
     homely
    -0.06
     farmer
    -0.06
     بهره
    -0.06
     elér
    -0.06
     brimming
    -0.06
     farmers
    -0.06
     Humboldt
    -0.05
    🥰
    -0.05
    POSITIVE LOGITS
     ਤੋਂ
    0.07
     ছাড়াও
    0.07
     Xperia
    0.06
     paraly
    0.06
     insult
    0.06
     помимо
    0.06
     Ainda
    0.06
     Halifax
    0.06
     البريط
    0.06
     vielä
    0.06
    Activations Density 0.003%

    No Known Activations