© 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. 59707
    Prev
    Next
    INDEX
    Explanations

    re- prefix

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

    The neuron specifically fires on the subword “re” (the common English prefix or stem “re-”) wherever it appears.

    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
     a
    -2.20
     by
    -2.02
     bekannten
    -1.87
     for
    -1.84
     have
    -1.81
     to
    -1.59
     may
    -1.57
     on
    -1.55
     –
    -1.54
     time
    -1.50
    POSITIVE LOGITS
     elektrik
    1.98
     ￥
    1.90
    푆
    1.88
    鰱
    1.82
    roud
    1.79
    毟
    1.79
     beslu
    1.71
     araba
    1.69
     Putri
    1.68
     fokus
    1.67
    Activations Density 0.114%

    No Known Activations