© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12449
    Prev
    Next
    INDEX
    Explanations

    soil and soil health

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

    The neuron fires on mentions of soil and related growing‐condition terms (e.g. soil science, well-drained or bio-diverse soil, adequate water, sunlight).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ઔ
    0.65
    tFileInputExcel
    0.60
     ペンダント
    0.59
     വ്യാപ
    0.58
     appliances
    0.57
     Appliances
    0.55
    openqa
    0.55
     ikan
    0.54
    🐉
    0.54
    🐋
    0.54
    POSITIVE LOGITS
     soil
    2.77
     Soil
    2.53
    Soil
    2.52
     soils
    2.50
     Soils
    2.31
    土壤
    2.30
    soil
    2.25
    土
    2.03
     土
    1.91
     मिट्टी
    1.88
    Activations Density 0.416%

    No Known Activations