© 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. 128627
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on angle-bracket tokens (e.g. “<”) that signal HTML or markup elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     no
    -0.86
     grave
    -0.85
    说出
    -0.81
    说得
    -0.78
    their
    -0.77
     médias
    -0.75
    potentially
    -0.74
    mainly
    -0.73
     doz
    -0.73
    咱
    -0.73
    POSITIVE LOGITS
     darbu
    0.91
     venerdì
    0.84
     altid
    0.83
     lunedì
    0.82
     тако
    0.81
    joyed
    0.81
     lainnya
    0.80
     Зо
    0.80
     robić
    0.79
     viena
    0.78
    Activations Density 0.069%

    No Known Activations