© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15660
    Prev
    Next
    INDEX
    Explanations

    water systems and infrastructure

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

    topics related to water systems, environmental conservation, and water infrastructure.

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

    This neuron activates on terms and phrases relating to water and environmental management topics, such as water bodies, water treatment and quality, runoff sources, and related ecological or safety concerns.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ألعاب
    -1.29
    Ȩ
    -1.24
    <td>
    -1.20
    closedir
    -1.16
     различни
    -1.13
    蔦
    -1.12
    Юлия
    -1.11
    初め
    -1.09
    Наталья
    -1.09
     såsom
    -1.09
    POSITIVE LOGITS
     if
    1.44
     we
    1.24
     modificare
    1.17
    ά
    1.17
     affitto
    1.15
     если
    1.13
     jeśli
    1.09
     specchio
    1.07
     farsi
    1.05
     creare
    1.04
    Activations Density 0.394%

    No Known Activations