© 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. 70737
    Prev
    Next
    INDEX
    Explanations

    sustained injury or damage

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

    The neuron responds to words that describe someone sustaining or suffering a physical injury.

    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
     and
    -1.77
    ATION
    -1.54
     它
    -1.52
    ServletConfig
    -1.51
    {
    -1.50
    ти
    -1.47
    知らせ
    -1.43
     UIButton
    -1.42
     Which
    -1.41
     нашей
    -1.40
    POSITIVE LOGITS
    \
    1.88
     blistering
    1.68
    ↵
    1.68
     iNdEx
    1.50
    </h2>
    1.46
     importanza
    1.45
    绌
    1.42
    </em>
    1.41
     barring
    1.38
     sizeable
    1.36
    Activations Density 0.011%

    No Known Activations