© 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. 22-GEMMASCOPE-RES-131K
    7. 65256
    Prev
    Next
    INDEX
    Explanations

    closing html tags

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

    The neuron fires on XML/HTML tag-name tokens (both in opening and closing tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     После
    -0.93
    ⽂
    -0.89
    相应的
    -0.88
     From
    -0.86
    xA
    -0.83
     entsprechende
    -0.82
    ÍA
    -0.80
    相应
    -0.79
     February
    -0.77
    回戦
    -0.77
    POSITIVE LOGITS
     nữa
    1.13
    </h4>
    1.09
     another
    1.05
     seigneur
    1.04
    !」
    1.00
     conftest
    1.00
     נוספת
    0.96
    </h5>
    0.93
     weiteren
    0.92
    を追加
    0.91
    Activations Density 0.002%

    No Known Activations