© 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. 34-GEMMASCOPE-RES-131K
    7. 93968
    Prev
    Next
    INDEX
    Explanations

    html meta tags and licensing

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

    This neuron fires on structural markup tokens—things like HTML tag openings (e.g. `<meta`) and comment‐bullet markers (`*`) that introduce document elements.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     relever
    -0.88
     refuser
    -0.88
    osoever
    -0.85
    actable
    -0.81
     carrots
    -0.81
     mey
    -0.80
     warunk
    -0.79
    ̞
    -0.78
    inaldo
    -0.78
    kten
    -0.77
    POSITIVE LOGITS
     and
    0.88
     seconds
    0.88
    uldron
    0.87
     longest
    0.87
     long
    0.85
     مفید
    0.74
    ReadAll
    0.74
    Verified
    0.73
    kauft
    0.73
     Nhưng
    0.73
    Activations Density 0.001%

    No Known Activations