© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50246
    Prev
    Next
    INDEX
    Explanations

    international peace

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the word “peace.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тур
    -0.84
     الرياضيه
    -0.82
    EMT
    -0.77
    Codes
    -0.77
    قدر
    -0.76
    рованный
    -0.75
     увлаж
    -0.75
     Morales
    -0.74
    TIT
    -0.74
    SDA
    -0.73
    POSITIVE LOGITS
     peace
    5.31
    peace
    3.84
     Peace
    3.83
    Peace
    3.61
     PEACE
    3.05
     peaceful
    2.89
     paix
    2.69
    PEACE
    2.67
    和平
    2.44
    平和
    2.25
    Activations Density 0.029%

    No Known Activations