© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57101
    Prev
    Next
    INDEX
    Explanations

    Cross Country

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

    The neuron is triggered by markup and code‐style tokens—e.g. HTML/XML tags, meta declarations, angle-bracket includes—i.e. parts of documents that look like structured code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     inom
    -0.83
     then
    -0.80
     judicia
    -0.78
    psfrag
    -0.77
     onPause
    -0.73
    침
    -0.73
    *}$
    -0.72
    removeAll
    -0.71
     assust
    -0.71
     minus
    -0.70
    POSITIVE LOGITS
    BIBLIOGRAPHY
    0.93
     vanguard
    0.85
    Referências
    0.80
     actualidad
    0.79
     mystique
    0.79
     사용
    0.79
    标题
    0.78
     Normdatei
    0.77
     কর
    0.77
     millennials
    0.76
    Activations Density 0.000%

    No Known Activations