© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119514
    Prev
    Next
    INDEX
    Explanations

    one that

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

    The neuron activates specifically on the word “one” whenever it appears as an indefinite numeral.

    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
    -1.89
    </h2>
    -1.66
     there
    -1.45
     are
    -1.45
    ”,
    -1.40
     as
    -1.40
     Despite
    -1.34
     an
    -1.33
     remain
    -1.31
     continues
    -1.31
    POSITIVE LOGITS
     that
    2.47
     naszej
    1.68
     когда
    1.68
     вашей
    1.59
    
    1.57
     ancienne
    1.55
     нашей
    1.52
    sandalia
    1.48
    迎来
    1.46
     unseren
    1.45
    Activations Density 0.038%

    No Known Activations