© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30221
    Prev
    Next
    INDEX
    Explanations

    inserting html content

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

    The neuron is selectively firing on literal HTML markup (e.g. “<br>”, “<a href=” etc.) embedded in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     complicado
    -0.74
    baarheid
    -0.70
     popoli
    -0.68
     rato
    -0.68
     learned
    -0.68
    lemented
    -0.67
    tać
    -0.66
    !\
    -0.65
     deur
    -0.65
    amycin
    -0.64
    POSITIVE LOGITS
     '<
    2.33
     "<
    2.25
    }<
    2.09
    ('<
    2.05
     `<
    2.03
    ="<
    1.74
    ("<
    1.73
    '<
    1.70
    )<
    1.68
    \<
    1.67
    Activations Density 0.033%

    No Known Activations