© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48915
    Prev
    Next
    INDEX
    Explanations

    weed and invasive species management

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

    content related to herbicides, pesticides and plant/weed management.

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

    The neuron fires most strongly on domain‐specific, multi‐syllabic content words—especially technical or scientific nouns.

    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
     robberies
    -0.94
     orchards
    -0.87
     FLASH
    -0.86
     robbery
    -0.82
     gemstones
    -0.80
     intrigues
    -0.79
     gemstone
    -0.77
     oliva
    -0.77
     chuy
    -0.76
    煽
    -0.75
    POSITIVE LOGITS
     weed
    1.28
     invasive
    1.25
     herbicide
    1.17
     invas
    1.14
     Invasive
    1.12
     eradication
    1.10
     infested
    1.02
     management
    0.98
     eradicate
    0.95
     invaded
    0.93
    Activations Density 0.008%

    No Known Activations