© 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. 10-GEMMASCOPE-RES-131K
    4. 124113
    Prev
    Next
    INDEX
    Explanations

    AUG start of reading frame

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

    biological and genetic terms in molecular biology contexts, particularly DNA/RNA sequences, reading frames, and codons.

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

    The neuron selectively fires on technical molecular-biology terms marking translation initiation and coding regions (e.g. “AUG,” “start codon,” “Met-tRNA,” “open reading frame,” “ribosomal”).

    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
     这
    -1.87
    栳
    -1.86
    "
    
    -1.80
    䜣
    -1.74
    f
    -1.62
    By
    -1.59
    -
    -1.58
    How
    -1.54
    可能有
    -1.53
     By
    -1.48
    POSITIVE LOGITS
     Its
    2.05
    président
    1.74
    鳙
    1.55
    呷
    1.55
    ſures
    1.55
    着她
    1.54
     énergie
    1.52
    咾
    1.49
    時間に
    1.48
    完了
    1.45
    Activations Density 0.028%

    No Known Activations