© 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. 34-GEMMASCOPE-RES-131K
    7. 32900
    Prev
    Next
    INDEX
    Explanations

    code and natural language separators

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

    The neuron strongly activates on HTML/XML markup delimiters (e.g. “<” or “</”), i.e. it detects HTML‐style tags.

    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
     paragraphe
    -1.30
     mètre
    -1.01
    uding
    -1.00
     THEIR
    -0.99
     próprias
    -0.99
    бѣ
    -0.97
     ceremonia
    -0.97
     }>
    -0.96
    heses
    -0.95
    çadas
    -0.95
    POSITIVE LOGITS
     también
    1.13
     également
    1.10
     também
    1.03
     tampoco
    0.99
     mientras
    0.97
     asimismo
    0.94
    mizuno
    0.92
     hecho
    0.91
     conocido
    0.90
     prácticamente
    0.90
    Activations Density 0.021%

    No Known Activations