© 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. 57390
    Prev
    Next
    INDEX
    Explanations

    ure compounds

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

    words containing "ure" such as "nureflex", "urethanes", "megaureter", and "Accenture".

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

    The neuron fires on any token containing the character sequence “ure.”

    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
    стреча
    -2.69
     overseeing
    -2.55
     favors
    -2.44
     honoring
    -2.42
    
    -2.38
    翃
    -2.34
    \
    -2.25
    (?)
    -2.25
     feront
    -2.23
    StoryboardSegue
    -2.22
    POSITIVE LOGITS
     bukanlah
    2.41
    URE
    2.41
     normaux
    2.27
     Whether
    2.23
     інші
    2.19
     Similarly
    2.19
    or
    2.16
     Beſ
    2.14
    ︓
    2.13
    ֢
    2.08
    Activations Density 0.018%

    No Known Activations