© 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. 80729
    Prev
    Next
    INDEX
    Explanations

    pronoun I or integral I

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

    The neuron strongly responds to the standalone capital letter “I” when used as a variable or operator in mathematical expressions.

    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
     {
    -2.97
    텃
    -2.20
    ズニー
    -2.13
    ઁ
    -2.11
    wohner
    -2.09
     okazji
    -2.08
     și
    -2.00
     土産
    -2.00
    cological
    -1.97
     стоковая
    -1.97
    POSITIVE LOGITS
     
    2.59
    に関して
    2.13
     Then
    2.02
    .
    2.02
    より
    1.97
     facilitar
    1.88
     comprises
    1.86
    在意
    1.82
     Ganzen
    1.80
     The
    1.78
    Activations Density 0.046%

    No Known Activations