© 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. 90378
    Prev
    Next
    INDEX
    Explanations

    amounts after "of"

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

    The neuron strongly activates on the preposition “of.”

    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
     it
    -1.90
     how
    -1.75
     HttpNotFound
    -1.67
    朥
    -1.64
     each
    -1.62
    ständen
    -1.59
    zeigt
    -1.58
    sprzed
    -1.57
     not
    -1.55
    komplet
    -1.54
    POSITIVE LOGITS
     kilka
    1.98
    =
    1.95
     será
    1.95
     is
    1.95
     jedynie
    1.71
     tenía
    1.68
     após
    1.63
    昳
    1.62
    ?
    1.62
     somente
    1.61
    Activations Density 0.082%

    No Known Activations