© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6749
    Prev
    Next
    INDEX
    Explanations

    contextual notes at the end

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

    This neuron responds to HTML/XML markup tokens (e.g. tags like `<h5>`, `<br>`, closing slashes, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    álisis
    0.59
     絶対
    0.58
     portas
    0.58
     CSF
    0.57
    ̊
    0.57
    ifrån
    0.56
     DEI
    0.55
    癡
    0.55
     sav
    0.55
     ultimi
    0.55
    POSITIVE LOGITS
    blockquote
    1.07
    embed
    0.88
    "><
    0.87
    iframe
    0.87
    figcaption
    0.85
    ><
    0.84
    nbsp
    0.82
    paragraph
    0.81
    img
    0.80
    =""
    0.79
    Activations Density 0.203%

    No Known Activations