© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64988
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags

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

    This neuron specifically fires on the “UA” token as seen in HTML meta tags (e.g. the X-UA-Compatible header).

    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
    づけ
    -1.17
    corrhi
    -1.05
     ||
    
    -1.05
    感のある
    -1.02
    場合があります
    -0.99
     voedsel
    -0.99
    を行いました
    -0.97
     and
    -0.96
    のでしょうか
    -0.95
     أجل
    -0.95
    POSITIVE LOGITS
    なので
    1.30
    大部分
    1.07
     for
    1.07
    igrette
    1.05
    するので
    1.02
    つまり
    1.02
    があります
    0.99
     vrai
    0.97
    風景
    0.96
    それも
    0.96
    Activations Density 0.040%

    No Known Activations