© 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. 34-GEMMASCOPE-RES-131K
    7. 92154
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    Python package and setup-related file content with high activation on code syntax elements like file paths, module imports, and package names.

    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
     recoveries
    -0.77
    SocketChannel
    -0.75
     recover
    -0.73
    SqlSession
    -0.69
    Santis
    -0.69
    Marks
    -0.68
     SDG
    -0.68
     recoverable
    -0.68
     assertions
    -0.68
     Midlands
    -0.68
    POSITIVE LOGITS
    DeclareMath
    0.91
     Philadelphia
    0.82
    Philadelphia
    0.79
    Pennsylvania
    0.77
    Pherson
    0.77
     スマホ
    0.76
     فرمان
    0.76
     sarili
    0.75
    ziert
    0.75
    Parque
    0.75
    Activations Density 0.037%

    No Known Activations