© 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. 57496
    Prev
    Next
    INDEX
    Explanations

    phosphate compounds and enzymes

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

    biochemical terms related to phosphate compounds like nucleotides, enzymes, and metabolic molecules.

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

    The neuron is highly sensitive to chemical names of phosphorylated compounds—especially nucleotide or glyceride derivatives denoted by “-phosphate,” “di-phosphate,” “tri-phosphate,” or position markers like “5′” and “2′.”

    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
    st
    -1.89
    he
    -1.84
    by
    -1.80
    ︕
    -1.80
    en
    -1.74
    be
    -1.74
    though
    -1.72
    ed
    -1.69
    er
    -1.65
    and
    -1.63
    POSITIVE LOGITS
     Without
    1.64
    伟大的
    1.56
    Править
    1.53
     noticeable
    1.52
     Shortly
    1.52
    Shortly
    1.49
     должны
    1.48
     TWO
    1.48
    สำหรับ
    1.47
     Before
    1.46
    Activations Density 0.159%

    No Known Activations