© 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. 25678
    Prev
    Next
    INDEX
    Explanations

    RNA and DNA concentration

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

    mentions of RNA, DNA, or genetic material in scientific contexts.

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

    The neuron strongly activates on mentions of RNA (and related molecular‐biology terms like cDNA, sequencing, and sample quality), i.e. technical references to nucleic‐acid analysis.

    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
    ompi
    -0.82
     Girlfriend
    -0.81
    setVertical
    -0.80
     Trường
    -0.78
    Fortune
    -0.76
    Synchronization
    -0.75
     Cabello
    -0.74
     bandeja
    -0.74
     tě
    -0.73
    OrderBy
    -0.73
    POSITIVE LOGITS
     concentration
    1.51
    concentration
    1.27
     Concentration
    1.27
     concentrations
    1.22
     Nano
    1.19
    Concentration
    1.10
     Concentrations
    1.08
     quality
    1.07
     spectrophoto
    1.06
     Nan
    1.05
    Activations Density 0.019%

    No Known Activations