© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100618
    Prev
    Next
    INDEX
    Explanations

    HTML line break tags

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

    HTML line break tags (`<br>` and `<br/>`).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is specially triggering on HTML line‐break markup (e.g. `<br/>` or `<br>`) 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
     this
    -1.84
     What
    -1.84
     and
    -1.80
    angsaan
    -1.77
     striving
    -1.74
     while
    -1.74
     after
    -1.73
     keep
    -1.66
     There
    -1.66
     which
    -1.66
    POSITIVE LOGITS
    卺
    2.28
     rigue
    2.05
    during
    2.02
     dát
    1.84
    romeda
    1.82
    鮰
    1.82
     starten
    1.81
     anderen
    1.81
    𓆏
    1.80
    beginning
    1.80
    Activations Density 0.015%

    No Known Activations