© 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. 34-GEMMASCOPE-RES-131K
    4. 90340
    Prev
    Next
    INDEX
    Explanations

    cell or cells

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

    MATLAB code and programming syntax elements.

    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
    Referencoj
    -0.73
     facies
    -0.69
     /\
    -0.68
    ńskich
    -0.66
    رامی
    -0.65
    )
    
    -0.65
     packers
    -0.65
     in
    -0.65
     gotas
    -0.65
    RELATION
    -0.65
    POSITIVE LOGITS
     cell
    2.47
    cell
    2.14
     CELL
    2.00
    Cell
    1.96
     Cell
    1.95
    CELL
    1.70
     cells
    1.68
     cellphone
    1.51
    getCell
    1.48
    cells
    1.45
    Activations Density 0.008%

    No Known Activations