© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    solute-related words and scientific contexts

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

    scientific or technical terms ending in "-ute", "-ion", or related to chemical/biological entities.

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

    The main thing this neuron does is detect mentions of solutes, especially in contexts of their transport, diffusion, or compartmentalization.

    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
    푉
    -1.76
    ߜ
    -1.76
     relativement
    -1.72
     vérifier
    -1.66
    푢
    -1.65
     verschillende
    -1.61
    
    -1.59
    嶮
    -1.58
     that
    -1.57
    穑
    -1.57
    POSITIVE LOGITS
     people
    1.91
     because
    1.81
     only
    1.79
     ONLY
    1.64
     Also
    1.56
    刧
    1.55
     comparable
    1.55
     unique
    1.54
    athion
    1.53
     on
    1.52
    Activations Density 0.112%

    No Known Activations