© 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. 58825
    Prev
    Next
    INDEX
    Explanations

    emission and excitation lines

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

    astronomical and scientific terminology related to nebulae, emission lines, and space objects.

    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
     Jewel
    -0.79
    restre
    -0.74
     Jdbc
    -0.71
    紜
    -0.70
     Inflation
    -0.70
    dut
    -0.70
     februari
    -0.69
     neutron
    -0.69
     DARK
    -0.69
    编辑
    -0.68
    POSITIVE LOGITS
     emission
    0.86
     indicator
    0.82
    Oster
    0.78
    Dien
    0.74
     Emissions
    0.74
     excitation
    0.73
     Pittman
    0.73
     indor
    0.72
    _{[
    0.71
     diagnostic
    0.71
    Activations Density 0.024%

    No Known Activations