© 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. 84634
    Prev
    Next
    INDEX
    Explanations

    plural nouns referring to collections of items

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

    The neuron is primarily triggered by plural nouns (i.e. words ending in an –s plural marker).

    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
     and
    -2.45
     or
    -2.30
     by
    -2.11
     through
    -2.09
     during
    -2.02
     because
    -1.94
     throughout
    -1.93
     while
    -1.86
     before
    -1.85
     using
    -1.80
    POSITIVE LOGITS
     REALLY
    1.95
    {
    1.94
     Identifying
    1.91
     ridiculously
    1.87
     VERY
    1.80
     Avoiding
    1.80
     fournis
    1.73
     nonchal
    1.73
     vantagens
    1.72
     delightfully
    1.68
    Activations Density 0.076%

    No Known Activations