© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68309
    Prev
    Next
    INDEX
    Explanations

    html script tags

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

    The neuron is strongly triggered by HTML `<script>` tags (i.e. the start of embedded JavaScript blocks).

    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
     様子
    -1.16
     作る
    -1.12
    hadapi
    -1.05
    Какво
    -1.04
     கி
    -1.03
    ॑
    -0.96
     grouped
    -0.94
    Amend
    -0.94
     Parce
    -0.92
     acompañada
    -0.92
    POSITIVE LOGITS
     that
    1.30
    if
    1.02
     将
    1.00
    ിൽ
    0.98
     Endocrinol
    0.96
    渽
    0.96
    
    0.96
    that
    0.95
    ولايات
    0.94
    nib
    0.93
    Activations Density 0.014%

    No Known Activations