© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60710
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to multiple entities

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

    This neuron responds to plural-person pronouns (e.g. “their,” “they’re,” “leur,” “dem,” “y’all”).

    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
    𖥦
    -2.80
    𖡼
    -2.55
    ztes
    -2.55
    ↵↵
    -2.39
    celotti
    -2.36
    τών
    -2.31
    あります
    -2.30
    ଝ
    -2.30
    
    -2.30
    ⁦
    -2.28
    POSITIVE LOGITS
     respective
    2.94
    _
    2.86
    0
    2.84
    他就
    2.66
     acclaimed
    2.66
     reaffirmed
    2.63
     适合
    2.63
     Ähn
    2.63
     to
    2.59
     incluem
    2.59
    Activations Density 0.001%

    No Known Activations