© 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. 10-GEMMASCOPE-RES-131K
    7. 47593
    Prev
    Next
    INDEX
    Explanations

    section beginnings

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

    The neuron detects HTML tag syntax—especially the “<” bracket and tag names like div or input.

    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
    емъ
    -1.28
     ක
    -1.16
     CommonModule
    -1.16
    didn
    -1.15
    噱
    -1.14
     beherr
    -1.12
     futur
    -1.09
    ⑊
    -1.08
    该公司
    -1.08
     ස
    -1.08
    POSITIVE LOGITS
    .
    1.61
     new
    1.40
     of
    1.30
     increases
    1.24
    ),
    1.21
     food
    1.20
     additional
    1.20
     increase
    1.20
     water
    1.18
     see
    1.16
    Activations Density 0.010%

    No Known Activations