© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13798
    Prev
    Next
    INDEX
    Explanations

    introduction / introduce

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

    The neuron strongly activates on section‐heading words and their variants that introduce a topic (e.g. “Introduction,” “introduces,” “Introducing”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Д
    0.66
    Declaration
    0.66
    Hint
    0.65
    ದ
    0.62
    पू
    0.61
    რ
    0.59
    のは
    0.59
    I
    0.59
    긁
    0.58
    l
    0.57
    POSITIVE LOGITS
     introdu
    1.51
    Introducing
    1.51
     introductions
    1.49
     Introducing
    1.49
     introduce
    1.48
    Introdu
    1.45
     Introduce
    1.45
     Introdu
    1.44
     introducing
    1.43
     introduced
    1.42
    Activations Density 0.063%

    No Known Activations