© 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. 90286
    Prev
    Next
    INDEX
    Explanations

    waste agricultural materials

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

    scientific articles about chemical treatments using natural materials for environmental remediation.

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

    This neuron primarily picks out numeric quantities and measurement values (e.g. numbers, percentages, and other numeric tokens) in scientific text.

    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
     molybdenum
    -0.93
    scatter
    -0.90
    ophobic
    -0.88
     Vitamina
    -0.88
     terbukti
    -0.86
    зму
    -0.84
    frastructure
    -0.84
     artikelen
    -0.83
    的表情
    -0.82
    𝕧
    -0.82
    POSITIVE LOGITS
     waste
    1.48
     agricultural
    1.26
     wastes
    1.19
     agro
    1.13
     cheap
    1.09
     agriculture
    1.06
     Waste
    1.06
     inexpensive
    1.05
     abundant
    0.98
     WASTE
    0.96
    Activations Density 0.107%

    No Known Activations