© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58562
    Prev
    Next
    INDEX
    Explanations

    markdown and code delimiters

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

    The neuron fires on formatting‐ and markup‐related tokens—HTML/Markdown tags (e.g. `<i>`, `</i>`), emphasis markers (`*`, `**`), table separators (`|`), list punctuation, and the numbers/delimiters used in such constructs.

    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
     then
    -1.66
     its
    -1.27
    気に入りの
    -1.20
    el
    -1.16
    ！”
    -1.14
     всего
    -1.13
    رأة
    -1.12
     PARENTS
    -1.12
    しゃれ
    -1.10
    今回は
    -1.09
    POSITIVE LOGITS
    aussian
    1.41
    ∵
    1.36
     bekämp
    1.33
     druh
    1.30
     χωρίς
    1.30
     ſal
    1.29
     evidencia
    1.27
    colazione
    1.27
    orted
    1.26
     models
    1.23
    Activations Density 0.010%

    No Known Activations