© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66697
    Prev
    Next
    INDEX
    Explanations

    html elements and attributes

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

    The neuron activates on HTML markup tokens—i.e. it detects HTML tags and related attribute names.

    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
     it
    -1.73
     some
    -1.56
     your
    -1.50
     včetně
    -1.48
     する
    -1.41
     kön
    -1.39
    -\\
    -1.38
     Szene
    -1.38
     July
    -1.36
     möjligt
    -1.36
    POSITIVE LOGITS
    7
    1.80
    νος
    1.80
     />
    1.78
    сті
    1.75
    4
    1.71
    ilitate
    1.66
    訁
    1.66
    以前
    1.66
    了一个
    1.63
    岖
    1.63
    Activations Density 0.010%

    No Known Activations