© 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. 34-GEMMASCOPE-RES-131K
    7. 90879
    Prev
    Next
    INDEX
    Explanations

    soil fertility and organic matter

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

    discussions about soil properties and agricultural or environmental practices.

    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_34/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
     płyn
    -0.91
     groei
    -0.88
    ขาว
    -0.85
    urals
    -0.83
    װ
    -0.83
    indon
    -0.82
     versehen
    -0.82
    lilla
    -0.81
    ваме
    -0.81
    DEVICE
    -0.79
    POSITIVE LOGITS
     fertility
    1.41
     nutrient
    1.11
     amendment
    1.05
     amendments
    1.03
     soil
    1.02
     nutritious
    1.01
     amending
    1.01
     structure
    1.01
     improve
    1.00
     nutrients
    0.98
    Activations Density 0.012%

    No Known Activations