© 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. 55939
    Prev
    Next
    INDEX
    Explanations

    cell types

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

    code elements related to cells in various programming contexts like spreadsheets, UI components, and data structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    டுத்த
    -0.90
    apparently
    -0.85
    资格
    -0.77
    青空
    -0.76
     apparently
    -0.73
     Làm
    -0.73
    ージ
    -0.72
    撤退
    -0.72
    ントリー
    -0.72
    なるほど
    -0.70
    POSITIVE LOGITS
     Cell
    1.38
    CELL
    1.27
     cell
    1.27
    Cell
    1.25
     CELL
    1.23
    cell
    1.20
     Cells
    1.05
    cells
    0.94
    ättning
    0.92
    治愈
    0.89
    Activations Density 0.042%

    No Known Activations