© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68585
    Prev
    Next
    INDEX
    Explanations

    art supplies and techniques

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

    The neuron detects mentions of art materials, tools, or specific crafting mediums.

    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
     that
    -1.88
     which
    -1.88
     will
    -1.66
    which
    -1.60
     whose
    -1.52
    man
    -1.43
    '
    -1.30
    лению
    -1.30
     except
    -1.29
     boi
    -1.29
    POSITIVE LOGITS
    ׇ
    1.37
    今年の
    1.34
    ﻻ
    1.30
     шоколад
    1.28
     recomendable
    1.28
    ROOMS
    1.25
     '*')
    1.24
    爾
    1.23
     muchas
    1.22
    jeni
    1.22
    Activations Density 0.059%

    No Known Activations