© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59983
    Prev
    Next
    INDEX
    Explanations

    DNA/RNA start codons and sequences

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

    DNA and RNA base sequences (nucleotide patterns like TGG, AAG, CTG).

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

    This neuron detects short contiguous strings of nucleotide letters (DNA/RNA k-mers like “ATG,” “GGG,” “UUAA,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Ва
    -1.58
    仕方ない
    -1.45
     voiture
    -1.45
    nad
    -1.39
    IN
    -1.39
    His
    -1.39
    IRE
    -1.38
     dessas
    -1.38
    ge
    -1.37
    standard
    -1.34
    POSITIVE LOGITS
     or
    1.80
    」、「
    1.68
    הם
    1.62
    mener
    1.60
     and
    1.52
    」,
    1.50
     any
    1.48
     丈
    1.44
    ützt
    1.44
     because
    1.44
    Activations Density 0.018%

    No Known Activations