© 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. 22-GEMMASCOPE-RES-131K
    4. 39814
    Prev
    Next
    INDEX
    Explanations

    HTML structure tags

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

    The neuron fires on HTML/XML element openings (e.g. “<div”, “<button”, etc.), i.e. on tokens that begin an HTML tag.

    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
     this
    -1.34
     there
    -1.23
     their
    -1.10
     its
    -1.07
     voir
    -1.06
    резать
    -1.04
    دیگر
    -0.98
    ATUM
    -0.97
     specific
    -0.96
     anything
    -0.96
    POSITIVE LOGITS
     gradualmente
    1.02
    viser
    1.01
    Hilsen
    1.01
     hippie
    0.98
    TestBed
    0.95
    といった
    0.94
    dramatic
    0.93
    صبحت
    0.93
    黯
    0.91
    Stap
    0.90
    Activations Density 0.002%

    No Known Activations