© 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. 65091
    Prev
    Next
    INDEX
    Explanations

    wars

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

    This neuron activates on the word “Wars,” especially when it appears in titles or event names.

    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
    鹋
    -2.81
    ſam
    -2.78
    昻
    -2.75
    溦
    -2.72
    鋮
    -2.66
    
    -2.61
    神
    -2.58
     is
    -2.58
    两年
    -2.55
    だったり
    -2.52
    POSITIVE LOGITS
    s
    3.52
    </strong>
    3.41
    to
    3.39
    It
    3.34
    We
    3.06
     If
    3.05
    Y
    2.98
    ar
    2.97
    L
    2.86
    та
    2.84
    Activations Density 0.004%

    No Known Activations