© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42610
    Prev
    Next
    INDEX
    Explanations

    glyco- derivatives

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

    The neuron detects the prefix "glyco-" in biochemical or medical terms related to glycoproteins and glycoconjugates.

    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_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
     But
    -2.69
     curiously
    -2.66
     Now
    -2.66
     These
    -2.59
     Similarly
    -2.28
     chiaro
    -2.25
     Fragen
    -2.22
     Interested
    -2.22
     Changing
    -2.19
     comical
    -2.17
    POSITIVE LOGITS
     bekämp
    2.38
     tatuajes
    2.33
    놋
    2.27
     skvě
    2.16
    Ꮂ
    2.13
    輅
    2.09
    蕷
    2.08
    n
    2.06
    arraycopy
    2.06
    ↵
    2.06
    Activations Density 0.010%

    No Known Activations