© 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. 20369
    Prev
    Next
    INDEX
    Explanations

    medal or medalists

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

    The neuron strongly activates on mentions of “medal” (and its variants), i.e. references to medals or medal awards.

    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
    恫
    -2.20
    取締
    -2.14
    迓
    -2.11
    ”？
    -2.05
    。　　
    -2.02
    欉
    -1.95
    柵
    -1.94
    岀
    -1.93
    end
    -1.91
    剽
    -1.89
    POSITIVE LOGITS
    genodigd
    2.75
     
    2.66
    尤其是
    2.52
    雱
    2.14
    を行い
    2.13
    饪
    2.13
     花纹
    2.11
    欲しい
    2.11
    selben
    2.09
    きれい
    2.09
    Activations Density 0.008%

    No Known Activations