© 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. 34-GEMMASCOPE-RES-131K
    7. 84198
    Prev
    Next
    INDEX
    Explanations

    on the table

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

    The neuron detects the idiomatic phrase “bring(s) … to the table.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ajú
    -0.79
    gië
    -0.74
    fft
    -0.74
     Ewing
    -0.69
    ског
    -0.69
    ISTICAL
    -0.68
     VK
    -0.68
     kritik
    -0.68
    куль
    -0.67
    довал
    -0.67
    POSITIVE LOGITS
     table
    5.66
     Table
    4.16
    Table
    3.98
    table
    3.80
    TABLE
    3.16
     tables
    3.09
     TABLE
    3.02
    テーブル
    2.80
    getTable
    2.70
    ToTable
    2.30
    Activations Density 0.013%

    No Known Activations