© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43571
    Prev
    Next
    INDEX
    Explanations

    nouns following commas

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

    The neuron strongly activates on comma tokens, essentially detecting commas in the text.

    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
    -1.91
      
    -1.84
     you
    -1.67
    霎
    -1.66
     they
    -1.63
     tiroirs
    -1.62
    ↵
    -1.52
     proporcion
    -1.52
    ⟣
    -1.51
     qualquer
    -1.50
    POSITIVE LOGITS
     what
    2.06
    ٶ
    1.81
    Every
    1.65
     both
    1.63
    Like
    1.62
    what
    1.61
    Before
    1.60
     some
    1.58
     an
    1.58
     such
    1.55
    Activations Density 0.635%

    No Known Activations