© 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. 10-GEMMASCOPE-RES-131K
    7. 73171
    Prev
    Next
    INDEX
    Explanations

    html tag elements

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

    This neuron fires strongly on HTML tag tokens (e.g. the opening “<legend>” or “<div>” 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_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
    5
    -2.25
    2
    -2.20
    6
    -2.09
    4
    -2.08
    3
    -1.98
    7
    -1.97
    1
    -1.93
     but
    -1.91
    .
    -1.86
    0
    -1.77
    POSITIVE LOGITS
    晔
    1.63
    戆
    1.62
     farlo
    1.56
    emplares
    1.56
    áska
    1.55
     successivamente
    1.51
    隳
    1.50
     from
    1.49
    entistas
    1.48
    ecé
    1.48
    Activations Density 0.022%

    No Known Activations