© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10457
    Prev
    Next
    INDEX
    Explanations

    ammonia and ammonium compounds

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

    The neuron detects chemical formulas and terminology related to ammonia (NH3/NH4) and ammonium compounds.

    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
     aptly
    -1.81
     usata
    -1.79
    一個
    -1.73
     utilizzata
    -1.72
    la
    -1.72
     freuen
    -1.70
     idyllic
    -1.70
     rufen
    -1.68
    
    -1.65
    ……”
    -1.60
    POSITIVE LOGITS
    ↵↵
    1.88
    鴴
    1.62
    ፳
    1.61
    .
    1.58
    出声
    1.54
    鴬
    1.54
    其妙
    1.53
    [
    1.52
    locks
    1.48
    
    1.47
    Activations Density 0.007%

    No Known Activations