© 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. 60059
    Prev
    Next
    INDEX
    Explanations

    mRNA expression levels

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

    RNA and gene expression terminology in scientific papers.

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

    The neuron strongly activates on tokens containing digits—i.e. numeric quantities or identifiers (like “1,” “4,” or gene/protein names with numbers).

    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
    Toxicity
    -0.79
    ември
    -0.79
     болезни
    -0.79
    
    -0.77
     uParam
    -0.76
    お
    -0.75
    ῆς
    -0.74
    står
    -0.73
     passando
    -0.71
    教程
    -0.71
    POSITIVE LOGITS
     mRNA
    2.81
    mRNA
    2.00
     levels
    1.65
     messenger
    1.64
     transcript
    1.54
     level
    1.37
     expression
    1.36
     Levels
    1.34
    Levels
    1.34
     transcripts
    1.34
    Activations Density 0.429%

    No Known Activations