© 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. 114193
    Prev
    Next
    INDEX
    Explanations

    starting words for phrases

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

    The neuron is detecting HTML emphasis markup, specifically the opening <em> tag.

    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
     adecuados
    -1.70
     generado
    -1.68
     współpracy
    -1.63
     realizacji
    -1.60
     joyas
    -1.60
     personer
    -1.59
    的那种
    -1.55
    尋找
    -1.53
     joyería
    -1.50
    ꪹ
    -1.50
    POSITIVE LOGITS
    </strong>
    1.92
     while
    1.77
    ↵
    1.55
     mientras
    1.44
     semua
    1.42
     ۱۲
    1.41
     ۱۶
    1.37
     ۱۴
    1.35
    while
    1.34
     whereas
    1.27
    Activations Density 0.000%

    No Known Activations