© 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. 89999
    Prev
    Next
    INDEX
    Explanations

    biological transcript or mRNA

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

    scientific text with a focus on transcript or RNA-related terminology in academic research papers.

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

    The neuron strongly activates on technical, domain‐specific terms and phrases (especially uppercase or multi‐syllabic tokens) typical of scientific research write-ups.

    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
     bitmap
    -0.76
     knees
    -0.73
    (!_
    -0.72
     tabled
    -0.67
    мино
    -0.66
    anyuan
    -0.66
     Columbus
    -0.65
     sport
    -0.65
    navigationItem
    -0.65
    
    -0.65
    POSITIVE LOGITS
     transcript
    3.86
     transcripts
    3.84
    transcript
    3.28
     mRNA
    3.17
     Transcript
    3.09
     transcrip
    3.00
    Transcript
    2.97
     RNA
    2.63
    mRNA
    2.58
     transcriptional
    2.30
    Activations Density 0.242%

    No Known Activations