© 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. 54322
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and scientific terms

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

    scientific and technical terms, especially chemical compounds, anatomical structures, and specialized nomenclature.

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

    The neuron detects long, domain-specific terms and proper names—i.e. multi-token technical or scientific vocabulary.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -2.33
     and
    -1.89
     with
    -1.81
     not
    -1.81
     has
    -1.80
    ;
    -1.79
     on
    -1.64
     in
    -1.64
     was
    -1.57
     etc
    -1.57
    POSITIVE LOGITS
     ซึ่ง
    2.13
     a
    2.02
     یکی
    1.93
     což
    1.89
    ،
    1.88
    ,
    1.88
     وهو
    1.84
     imprimer
    1.66
     rembourse
    1.66
     fréqu
    1.66
    Activations Density 0.271%

    No Known Activations