© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30244
    Prev
    Next
    INDEX
    Explanations

    functional enrichment analysis

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

    text related to data analysis, particularly functional enrichment analysis in bioinformatics and genomics research.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting highly specialized technical or methodological terms (especially in bioinformatics/data‐analysis contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    CLT
    -0.87
    maria
    -0.80
    nisch
    -0.79
    Stade
    -0.73
     Kaffee
    -0.72
    גיש
    -0.72
    裳
    -0.71
     христи
    -0.71
     правило
    -0.69
     محبوب
    -0.69
    POSITIVE LOGITS
     enrichment
    2.00
     Enrichment
    1.65
     enriched
    1.51
     enrich
    1.50
    richment
    1.29
     enriching
    1.13
     enriquec
    1.12
    Term
    1.09
     functional
    1.09
    terms
    1.07
    Activations Density 0.035%

    No Known Activations