© 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. 11348
    Prev
    Next
    INDEX
    Explanations

    preposition in

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

    The neuron strongly activates on the standalone preposition “in.”

    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
     you
    -2.81
     there
    -1.87
     think
    -1.67
    胳
    -1.55
     people
    -1.51
    玙
    -1.51
     którą
    -1.48
     katholischen
    -1.48
    瑋
    -1.45
    捶
    -1.45
    POSITIVE LOGITS
     a
    2.42
     múl
    1.52
    两
    1.39
    ровал
    1.31
    ță
    1.30
     ہے۔
    1.28
    цію
    1.26
     mengen
    1.25
    "
    1.25
    "",
    1.24
    Activations Density 0.058%

    No Known Activations