© 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. 55684
    Prev
    Next
    INDEX
    Explanations

    html class attributes

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

    This neuron detects equal-sign assignments—that is, the “=” used in code or markup to assign attribute/property values.

    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
     Hispan
    -0.79
    URDAY
    -0.73
     électronique
    -0.73
     Natsu
    -0.72
     temb
    -0.70
     BUDGET
    -0.70
     hiz
    -0.69
    ERAL
    -0.69
     puppet
    -0.69
     чет
    -0.68
    POSITIVE LOGITS
     verfol
    0.94
     gehör
    0.93
    ksiä
    0.85
    ospels
    0.79
     new
    0.77
     Zusammen
    0.77
    🧓
    0.76
     prachtige
    0.75
     dzięki
    0.73
     herself
    0.73
    Activations Density 0.001%

    No Known Activations