© 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. 22-GEMMASCOPE-RES-131K
    7. 34761
    Prev
    Next
    INDEX
    Explanations

    html, htm, pdf links

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

    This neuron responds strongly to HTML markup (e.g. anchor tags and related tags/keywords) embedded in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     cilvē
    -1.03
    =
    -0.99
    上述
    -0.94
    leveland
    -0.93
     és
    -0.89
    二十四
    -0.82
    ShowDialog
    -0.82
     World
    -0.81
    photographe
    -0.81
     sql
    -0.80
    POSITIVE LOGITS
     šaty
    1.02
    もあって
    1.01
    Pengertian
    1.00
    ferien
    0.98
     dáms
    0.97
    来越
    0.96
     rafraî
    0.95
     modrá
    0.94
     červená
    0.94
    معرفی
    0.94
    Activations Density 0.075%

    No Known Activations