© 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. 87268
    Prev
    Next
    INDEX
    Explanations

    cardiomy affected by opathy

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

    words related to technical or specialized terminology in computing, medicine, and science.

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

    The neuron fires on subword fragments that form the stems of technical compound terms—e.g. parts of identifiers in code (readline, SHA1 fingerprint, bookmarkable_id) or medical terms (cardiomy– in cardiomyopathy).

    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
    "
    -4.97
    2
    -4.09
    1
    -3.95
    3
    -3.86
    7
    -3.84
    6
    -3.52
    4
    -3.52
    8
    -3.42
    5
    -3.19
    9
    -3.11
    POSITIVE LOGITS
    我们要
    3.20
    我们会
    3.17
     馆
    3.00
    
    2.98
    玙
    2.97
    听到了
    2.95
    ”،
    2.94
    汌
    2.94
    튿
    2.89
    赈
    2.86
    Activations Density 0.007%

    No Known Activations