© 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. 13893
    Prev
    Next
    INDEX
    Explanations

    blog post urls ending in .html

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

    The neuron consistently lights up on the “html” file‐extension tokens in URLs (i.e. the “.html” suffix).

    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
     of
    -1.59
    🤞
    -1.40
    が
    -1.37
    —
    -1.29
    +*
    -1.27
    te
    -1.25
    у
    -1.25
    *"
    -1.24
    ............
    -1.23
    ._.
    -1.23
    POSITIVE LOGITS
     velocidades
    1.48
    Penjelasan
    1.48
    Tils
    1.48
    Lokal
    1.47
    Vra
    1.45
     costuras
    1.45
    Grafik
    1.43
    Kunden
    1.41
    Ausgabe
    1.41
    Paket
    1.41
    Activations Density 0.008%

    No Known Activations