© 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. 22-GEMMASCOPE-RES-131K
    7. 39519
    Prev
    Next
    INDEX
    Explanations

    HTML label tags

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

    This neuron activates on HTML element tag names (e.g., legend, label, span) in markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.35
    calciatore
    -1.12
     operation
    -1.09
    它的
    -1.09
    Quién
    -1.01
    Quando
    -0.99
     kapat
    -0.98
    estä
    -0.97
    ченной
    -0.96
    ysl
    -0.94
    POSITIVE LOGITS
     for
    1.23
    <>
    1.13
    じゃあ
    1.02
    enfone
    1.02
    xler
    1.00
    ૪
    1.00
     więc
    0.99
    情况
    0.99
     pido
    0.99
    骆
    0.98
    Activations Density 0.001%

    No Known Activations