© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41549
    Prev
    Next
    INDEX
    Explanations

    Viscount Preston

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

    The neuron is specialized to detect East‐Asian corner‐style quotation or title brackets (e.g. 「『』」 and 「《》」).

    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
    это
    -2.41
     ciertamente
    -2.30
     aislados
    -2.22
     básicamente
    -2.22
     muchísimo
    -2.20
    趼
    -2.17
     cuán
    -2.14
    いますが
    -2.09
     verhind
    -2.09
     particularmente
    -2.08
    POSITIVE LOGITS
    “.
    2.70
    ᠂
    2.45
    ࿚
    2.45
    蠵
    2.44
     have
    2.34
     esteemed
    2.28
    л
    2.19
     dalam
    2.16
     como
    2.16
    o
    2.14
    Activations Density 0.001%

    No Known Activations