© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16589
    Prev
    Next
    INDEX
    Explanations

    html paragraph tags

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

    The neuron specifically detects HTML paragraph tag tokens (the “p” in `<p>`/`</p>`).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     to
    -2.47
    lorus
    -1.52
    */)
    -1.51
    >())
    -1.49
    uellement
    -1.48
    氿
    -1.47
     >/
    -1.45
    ']:
    -1.45
    ):
    -1.42
    高原
    -1.41
    POSITIVE LOGITS
     
    1.66
     disfraz
    1.56
    精美
    1.52
     \
    1.48
    是非常
    1.47
    on
    1.46
     shattered
    1.41
    是很
    1.41
    In
    1.40
     halted
    1.39
    Activations Density 0.003%

    No Known Activations