© 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. 38515
    Prev
    Next
    INDEX
    Explanations

    acronyms and technical terms

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

    This neuron responds to uppercase or capitalized terms—especially acronyms and proper 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
    櫪
    -3.25
    鳯
    -2.80
    𖤍
    -2.66
    〬
    -2.64
    𝄆
    -2.61
    琑
    -2.61
    顒
    -2.56
    mtable
    -2.55
    ظمة
    -2.52
     लेकिन
    -2.50
    POSITIVE LOGITS
    蹕
    3.11
    媜
    3.05
    0
    3.02
    {
    2.94
    </h3>
    2.94
    This
    2.91
    毉
    2.83
    芣
    2.78
    </strong>
    2.72
    觧
    2.66
    Activations Density 0.025%

    No Known Activations