© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33501
    Prev
    Next
    INDEX
    Explanations

    soil and salinity degradation

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

    This neuron activates for content related to soil, land, and environmental contexts, particularly focusing on soil contamination, conservation, and agricultural topics.

    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
    ijiet
    -0.81
    issage
    -0.79
    выя
    -0.78
    zysty
    -0.76
    ILITY
    -0.75
    perative
    -0.74
     Corintios
    -0.73
    反应
    -0.73
    setup
    -0.72
     kayak
    -0.71
    POSITIVE LOGITS
     deser
    1.88
     degradation
    1.57
     land
    1.37
     soil
    1.32
     degraded
    1.29
     Degradation
    1.26
    degradation
    1.25
     degrade
    1.07
     degra
    1.06
    Soil
    1.02
    Activations Density 0.013%

    No Known Activations