© 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. 47125
    Prev
    Next
    INDEX
    Explanations

    genes, transcription, development

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

    genes and transcription factors in biology research papers, particularly focusing on MADS-box and HOX genes.

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

    The neuron activates strongly on mentions of MADS‐box transcription factor genes (e.g. “OsMADS6,” “AGAMOUS‐like,” “MADS‐box” identifiers).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    тенок
    -0.75
     currency
    -0.73
     cc
    -0.70
    membrane
    -0.70
     Cow
    -0.69
     lang
    -0.69
     rodz
    -0.68
    kilde
    -0.68
    dk
    -0.68
    accio
    -0.68
    POSITIVE LOGITS
     cadast
    0.93
     home
    0.89
    ехать
    0.88
     amorti
    0.87
    home
    0.83
     determin
    0.82
    resumen
    0.79
    efeller
    0.77
     AirPods
    0.77
     patterning
    0.76
    Activations Density 0.122%

    No Known Activations