© 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. 99727
    Prev
    Next
    INDEX
    Explanations

    table separators and structure

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

    This neuron detects table elements—especially pipes (“|”), separator dashes (“---”), and numeric cell entries—in formatted (e.g. Markdown‐style) tables.

    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
    桄
    -1.34
    ⦊
    -1.34
     the
    -1.30
     یکی
    -1.30
    相比
    -1.24
    其它
    -1.24
    nemen
    -1.23
     教程
    -1.23
    gegen
    -1.22
     anderen
    -1.20
    POSITIVE LOGITS
    logio
    1.27
     obligatorio
    1.20
    crom
    1.19
     deseado
    1.15
     obligado
    1.15
    EDES
    1.13
     fijo
    1.12
    𝜋
    1.11
     mundos
    1.11
    cester
    1.10
    Activations Density 0.022%

    No Known Activations