© 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. 115574
    Prev
    Next
    INDEX
    Explanations

    agricultural land and productivity

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

    descriptions of agricultural land, particularly mentions of acres, farmland, and soil quality.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of land‐area quantities, especially numeric measurements (e.g. acres) describing agricultural or farmland area.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     materiales
    -0.99
    anciers
    -0.87
     materialen
    -0.86
     materiais
    -0.82
     GRATU
    -0.81
     Rigidbody
    -0.80
    ீர
    -0.79
     materiali
    -0.79
    ạn
    -0.78
    lickr
    -0.78
    POSITIVE LOGITS
     productive
    1.91
     agricultural
    1.71
     arable
    1.63
     farmland
    1.55
    productive
    1.41
     fertile
    1.34
     productivity
    1.34
     culti
    1.27
    耕
    1.23
     Productive
    1.21
    Activations Density 0.024%

    No Known Activations