© 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. 75164
    Prev
    Next
    INDEX
    Explanations

    ipsilateral medical terms

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

    anatomical terms describing the relative position of body parts, particularly "ipsilateral" and "contralateral".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron identifies mentions of anatomical laterality, highlighting terms like “ipsilateral” or “contralateral.”

    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
    ing
    -1.95
     *
    -1.66
     
    -1.63
     <
    -1.63
     oficial
    -1.61
    -1.55
     стены
    -1.55
    他の
    -1.52
    嘚
    -1.49
     diferente
    -1.46
    POSITIVE LOGITS
    쫀
    1.79
    比如说
    1.73
    榦
    1.69
    郏
    1.62
    我们会
    1.59
     greateſt
    1.59
    لباس
    1.59
     餐厅
    1.58
    豋
    1.57
     ダウンロード
    1.55
    Activations Density 0.006%

    No Known Activations