© 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. 75494
    Prev
    Next
    INDEX
    Explanations

    bomber, bombers, Bombardier

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

    The neuron strongly activates on mentions of “bomber” (and closely related forms like “Bombers” or “Bombardier”).

    oai_token-act-pair · o4-miniTriggered 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
    acterísticas
    -3.03
     leaſt
    -2.86
    ㍑
    -2.69
     ответил
    -2.59
    苼
    -2.56
    ﺅ
    -2.52
    bzw
    -2.45
     стоковая
    -2.44
    pulseira
    -2.42
    ቕ
    -2.42
    POSITIVE LOGITS
    the
    3.23
    e
    2.81
    i
    2.70
     группы
    2.58
    .
    2.50
    –
    2.47
    とは言
    2.42
     accordance
    2.36
     eines
    2.34
    ка
    2.30
    Activations Density 0.003%

    No Known Activations