© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104434
    Prev
    Next
    INDEX
    Explanations

    code and sequences

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

    method calls that modify CSS classes, particularly `addClass`, `removeClass`, `toggleClass`, and `hasClass`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron highlights jQuery DOM methods that include “Class” in their name (e.g. addClass, removeClass, toggleClass, hasClass).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </h3>
    -3.06
    for
    -2.22
    筱
    -2.05
    ípios
    -1.97
    參見
    -1.91
    लाइन
    -1.89
     diesmal
    -1.79
    🌸
    -1.77
     deswegen
    -1.70
     RURAL
    -1.70
    POSITIVE LOGITS
    </b>
    2.78
     古着
    2.03
     entsprechende
    1.99
    很容易
    1.95
     hebben
    1.93
     sogenannte
    1.91
     bytu
    1.91
    ѻ
    1.90
     eigentliche
    1.88
     wichtigste
    1.88
    Activations Density 0.001%

    No Known Activations