© 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. 68531
    Prev
    Next
    INDEX
    Explanations

    waste material remnants

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

    materials in manufacturing and industrial processes, particularly small particles like cuttings, scraps, shards, and grains.

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

    The neuron fires on technical nouns that name solid particulates, debris, or byproducts in industrial processes.

    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
     tienen
    -1.66
    悒
    -1.30
    in
    -1.30
     hamil
    -1.29
     reducing
    -1.29
     increased
    -1.27
     experiencing
    -1.27
    other
    -1.27
    although
    -1.27
     aspects
    -1.26
    POSITIVE LOGITS
    𖧵
    1.60
    尨
    1.54
     églises
    1.50
     endroits
    1.46
     itinéraires
    1.45
     tohoto
    1.41
     этого
    1.41
     régions
    1.40
     ว่า
    1.39
    の中から
    1.37
    Activations Density 0.081%

    No Known Activations