Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 411
    Prev
    Next
    INDEX
    Explanations

    measurement units (mg, kg, L, g, dL)

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

    This neuron detects unit measurements in scientific notation format like "mg/kg", "mg/L", or "g/L" in technical and medical documents.

    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
     cercano
    -1.64
    </strong>
    -1.61
    …”
    -1.58
    ?”
    -1.58
    ENZO
    -1.54
    [];
    
    -1.52
    )";
    
    -1.44
    ”:
    -1.43
     Amerikaanse
    -1.43
    用来
    -1.42
    POSITIVE LOGITS
    2
    2.20
    6
    1.89
    3
    1.72
    我这
    1.72
    7
    1.68
    5
    1.67
    8
    1.59
    儅
    1.50
     /
    1.41
     the
    1.39
    Activations Density 0.019%

    No Known Activations