© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113507
    Prev
    Next
    INDEX
    Explanations

    following "to" with a verb

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

    The neuron activates on the infinitival marker “to” (i.e. instances of the word “to”).

    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
     burgeoning
    -1.84
     größer
    -1.81
    他说
    -1.73
    同上
    -1.73
    isation
    -1.72
     هستند
    -1.70
     کردم
    -1.66
     französische
    -1.66
    箭头
    -1.66
     laterales
    -1.65
    POSITIVE LOGITS
     be
    2.28
    {
    2.03
     essas
    1.95
    EdgeInsets
    1.92
    喾
    1.86
    1.78
    ühungen
    1.78
     `
    1.77
    дения
    1.77
     Endlich
    1.76
    Activations Density 0.067%
    No Known Activations