© 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. 127233
    Prev
    Next
    INDEX
    Explanations

    defines concepts using refers to

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

    The neuron fires on definitional phrases—especially the “refers to” construction that introduces a definition.

    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
     on
    -2.02
     one
    -1.73
     al
    -1.73
    骨折
    -1.67
     all
    -1.61
     as
    -1.60
     up
    -1.59
     out
    -1.56
    疑惑
    -1.55
    孳
    -1.55
    POSITIVE LOGITS
     باسلام
    2.08
     anunció
    2.06
     både
    1.83
    “
    1.81
    臜
    1.79
     komende
    1.74
     anuncia
    1.73
    谖
    1.73
    枼
    1.73
    
    1.73
    Activations Density 0.073%

    No Known Activations