© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59294
    Prev
    Next
    INDEX
    Explanations

    nucleotide and DNA sequences

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

    DNA and genetic sequences, especially when discussing nucleotides, genes, and molecular biology concepts.

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

    The neuron responds to very common tokens by their frequency, i.e. it activates strongly on words that occur frequently in the document.

    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
     Soil
    -0.78
    maillot
    -0.75
     Anzahl
    -0.73
    ansom
    -0.70
     Touren
    -0.70
    ۚ
    -0.69
     Einstellung
    -0.69
    裤
    -0.69
     joyas
    -0.68
    นะนำ
    -0.68
    POSITIVE LOGITS
     sequence
    3.86
     sequences
    3.55
    sequence
    3.19
    Sequence
    3.00
     Sequences
    2.92
     Sequence
    2.86
     SEQUENCE
    2.69
    sequences
    2.64
    序列
    2.59
    Sequences
    2.56
    Activations Density 0.259%

    No Known Activations