© 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. 6691
    Prev
    Next
    INDEX
    Explanations

    Xunit; Saïd El; Saeed Aj; ivanoats; acrylamide gel

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

    names from various language backgrounds, particularly in technical or programming contexts.

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

    This neuron detects proper names—capitalized named entities such as personal names, titles, genus names, organization or framework names.

    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
    </h1>
    -2.94
     ‘
    -2.63
    \
    -2.61
     \
    -2.39
    粜
    -2.28
    最も
    -2.27
     современной
    -2.23
    本当に
    -2.19
    </b>
    -2.17
    鴴
    -2.17
    POSITIVE LOGITS
     assolu
    2.77
    [%
    2.61
    “
    2.59
    ⭐
    2.39
     deswegen
    2.36
    s
    2.31
    "%
    2.31
    ی
    2.30
     estrema
    2.28
     această
    2.22
    Activations Density 0.077%

    No Known Activations