© 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. 54345
    Prev
    Next
    INDEX
    Explanations

    chemical synthesis and evaluation

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

    This neuron identifies technical chemistry terms and chemical nomenclature, particularly focusing on chemical synthesis descriptions and compound names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    lihood
    -0.83
     ilustrasi
    -0.80
    HOU
    -0.80
    Γ
    -0.79
     разобра
    -0.78
    NUT
    -0.78
     Pilihan
    -0.77
    istics
    -0.77
    ٹ
    -0.76
    technologies
    -0.76
    POSITIVE LOGITS
     substituted
    0.91
    quina
    0.82
    oncesto
    0.79
     Mann
    0.79
     bén
    0.77
    ᥕ
    0.76
     Sail
    0.76
     multicultural
    0.76
     Schiff
    0.75
     Perkin
    0.75
    Activations Density 0.109%

    No Known Activations