© 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. 34-GEMMASCOPE-RES-131K
    7. 99554
    Prev
    Next
    INDEX
    Explanations

    CSS classes, HTML tags, and descriptive headings

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

    The neuron strongly activates on tokens belonging to code snippets—especially HTML tags, CSS/Sass selectors, punctuation, and numeric values.

    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
    动漫
    -1.04
    ciatore
    -0.89
     Danube
    -0.85
    PubMed
    -0.82
     Sarasota
    -0.82
     rupee
    -0.82
    Phi
    -0.81
     notifications
    -0.81
    latable
    -0.80
    diabetic
    -0.80
    POSITIVE LOGITS
     California
    1.09
    Stanford
    0.96
     Menlo
    0.94
    California
    0.89
    nesota
    0.88
     CALIFORNIA
    0.88
     copertura
    0.85
     Stanford
    0.85
     california
    0.84
     San
    0.80
    Activations Density 0.019%

    No Known Activations