© 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. 10-GEMMASCOPE-RES-131K
    4. 119901
    Prev
    Next
    INDEX
    Explanations

    html tags with attributes

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

    HTML/JSX opening tags for common elements like `<div>`, `<p>`, `<main>`, `<button>`, and `<form>`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    Both
    -1.53
     both
    -1.51
     Both
    -1.41
     advirtió
    -1.41
     These
    -1.37
     this
    -1.32
    Achter
    -1.31
     The
    -1.25
     dwindling
    -1.25
     Ну
    -1.24
    POSITIVE LOGITS
    茈
    1.64
     seulement
    1.63
    olite
    1.52
     verres
    1.52
     apenas
    1.50
     único
    1.48
     uniquement
    1.45
     ciebie
    1.44
     kulak
    1.42
    艄
    1.42
    Activations Density 0.003%

    No Known Activations