© 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. 34-GEMMASCOPE-RES-131K
    4. 93685
    Prev
    Next
    INDEX
    Explanations

    HTML entities and spacing

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

    This neuron detects character‐encoding escape sequences—e.g. hex byte escapes like “\xe2\x8…” and HTML/XML numeric or named entities like “ ”.

    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
    cau
    -1.05
    κη
    -0.83
    dalla
    -0.76
    peripheral
    -0.76
    marina
    -0.75
    htar
    -0.74
    著名
    -0.74
     tepi
    -0.73
    aktur
    -0.73
     prič
    -0.70
    POSITIVE LOGITS
     space
    1.71
    SizedBox
    1.67
    nbsp
    1.66
     SizedBox
    1.57
    space
    1.47
    br
    1.41
     break
    1.38
     espacio
    1.38
     spaces
    1.34
    Space
    1.30
    Activations Density 0.087%

    No Known Activations