© 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. 75442
    Prev
    Next
    INDEX
    Explanations

    qPCR and related technical terms

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

    technical/scientific terms like PCR, qPCR, and programming-related concepts.

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

    The neuron is strongly triggered by tokens that are acronyms, CamelCase identifiers, or other strings containing internal uppercase letters (e.g. “SpringRunner,” “qPCR,” “RT-qPCR,” “quadruple,” 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
     “
    -3.14
      
    -2.81
    m
    -2.61
    蠖
    -2.48
     tą
    -2.42
    for
    -2.30
    d
    -2.27
     sturdy
    -2.23
    。“
    -2.23
    你不要
    -2.22
    POSITIVE LOGITS
    Despite
    3.20
     Despite
    2.78
    Although
    2.67
    Regardless
    2.66
    During
    2.61
    When
    2.52
    Unlike
    2.52
    〜〜
    2.50
     Currently
    2.50
    Though
    2.50
    Activations Density 0.001%

    No Known Activations