© 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. 10-GEMMASCOPE-RES-131K
    7. 9655
    Prev
    Next
    INDEX
    Explanations

    World War

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

    The neuron detects numeric tokens, especially three-digit numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of the World Wars (especially explicit references to World War I or II and their eras).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to World War I or World War II.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    㐂
    -1.71
    🪬
    -1.66
    ’)
    -1.66
    獁
    -1.64
    ……”
    -1.61
    晅
    -1.60
     夜景
    -1.59
    ୌ
    -1.58
    刧
    -1.58
    ねー
    -1.58
    POSITIVE LOGITS
    it
    1.96
    in
    1.95
     чего
    1.88
     imprescin
    1.63
    缡
    1.62
    ють
    1.59
    蹰
    1.59
     более
    1.56
    级的
    1.56
     we
    1.55
    Activations Density 0.003%

    No Known Activations