© 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. 75521
    Prev
    Next
    INDEX
    Explanations

    Web encoding and programming constructs

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

    This neuron detects programming tokens for escaping or encoding text (e.g. HTML escaping and URL‐encoding functions).

    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
    </b>
    -1.57
     exclusivo
    -1.53
    ȧ
    -1.52
     The
    -1.48
     atendido
    -1.45
    句话
    -1.37
     entendido
    -1.37
    鴞
    -1.35
    </h5>
    -1.35
     subjected
    -1.34
    POSITIVE LOGITS
    2
    2.08
    6
    2.00
    9
    1.98
    while
    1.73
    7
    1.66
     نداشته
    1.65
    4
    1.63
    睒
    1.60
    8
    1.57
    Surely
    1.53
    Activations Density 0.003%

    No Known Activations