© 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. 34805
    Prev
    Next
    INDEX
    Explanations

    Arabidopsis and plants

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

    citations in scientific papers, particularly author names and publication years in parentheses.

    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
     unrelenting
    -0.76
     countless
    -0.74
     encourages
    -0.72
    妾
    -0.69
     shortly
    -0.69
     moisture
    -0.69
     Moisture
    -0.69
     Patsy
    -0.68
    бовал
    -0.68
     confirms
    -0.68
    POSITIVE LOGITS
     Arabidopsis
    1.10
     plant
    1.05
     plants
    1.04
    Plants
    0.96
     Plant
    0.96
    Plant
    0.94
     Plants
    0.92
    plant
    0.92
    plants
    0.91
     Theolog
    0.90
    Activations Density 0.033%

    No Known Activations