© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130477
    Prev
    Next
    INDEX
    Explanations

    The neuron activates most strongly on the various “column” tokens in UI‐grid or table code (e.g. Column, Columns, DataGridColumn, col => …).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    column properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Править
    -1.05
    ˶
    -0.96
    ByType
    -0.96
    комнат
    -0.96
     reklama
    -0.96
    madı
    -0.93
    bảng
    -0.91
     October
    -0.91
    vertising
    -0.90
     llegaron
    -0.90
    POSITIVE LOGITS
     lég
    1.15
    czej
    1.04
    omaly
    1.02
     ili
    0.96
     olmak
    0.96
     parmi
    0.95
    <th>
    0.94
    erobic
    0.94
     включа
    0.93
    shown
    0.92
    Activations Density 0.008%

    No Known Activations