© 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. 22-GEMMASCOPE-RES-131K
    7. 38920
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

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

    This neuron strongly activates on second-person references—especially “you” (and “your”) directed at the reader or subject.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     won
    -1.02
    Which
    -0.88
    ी
    -0.85
    qué
    -0.85
     maille
    -0.84
     List
    -0.84
    ,
    -0.83
    Item
    -0.82
    List
    -0.82
     you
    -0.82
    POSITIVE LOGITS
    
    0.97
    productId
    0.89
    upported
    0.85
    tioner
    0.85
    ѳ
    0.84
     चुनें
    0.83
    ógio
    0.82
    Interes
    0.82
    primaryColor
    0.82
    reditation
    0.82
    Activations Density 0.013%

    No Known Activations