© 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. 15503
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and component names

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

    The neuron is detecting XML/HTML‐style tags (angle-bracket elements) and their attributes in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     таких
    -1.27
     such
    -1.13
     каждом
    -1.05
     Signore
    -1.05
    ,
    -1.02
     tellement
    -1.01
    \\
    -1.01
     такого
    -1.00
    such
    -0.99
    ↵↵↵
    -0.96
    POSITIVE LOGITS
    ﻷ
    1.51
    ΡΟ
    1.46
    pette
    1.41
    awarkan
    1.34
    unjukkan
    1.33
    ׇ
    1.26
    ',
    1.26
     nový
    1.24
     especí
    1.24
    Hvem
    1.23
    Activations Density 0.024%

    No Known Activations