© 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. 18968
    Prev
    Next
    INDEX
    Explanations

    crystalline compounds and materials

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

    This neuron activates for the word "crystalline" in scientific contexts.

    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
    
    -3.17
     {
    -2.94
     The
    -2.92
    躋
    -2.91
    ting
    -2.66
    鵙
    -2.53
    苤
    -2.53
     configurações
    -2.48
    慫
    -2.47
    
    -2.47
    POSITIVE LOGITS
    下一篇
    2.95
    璈
    2.92
    鄠
    2.89
    ｘ
    2.67
     灵
    2.64
    蒟
    2.63
    鷓
    2.61
    ⭏
    2.55
    ｛
    2.53
    本章
    2.50
    Activations Density 0.005%

    No Known Activations