© 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. 69305
    Prev
    Next
    INDEX
    Explanations

    his or her

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

    The neuron detects the coordinating “or” in the common “his or her” gendered-pronoun construction.

    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
    .......
    -1.73
     ....
    -1.71
    ....
    -1.68
     what
    -1.67
    さんです
    -1.66
    .....
    -1.55
     in
    -1.52
    "...
    -1.52
    ........
    -1.52
     Because
    -1.52
    POSITIVE LOGITS
     stalwart
    1.81
     スリム
    1.66
     poteva
    1.51
    たっぷり
    1.50
    倏
    1.48
     inizia
    1.48
     lauded
    1.47
                
    1.46
     extravag
    1.45
     specifiche
    1.44
    Activations Density 0.008%

    No Known Activations