© 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. 78872
    Prev
    Next
    INDEX
    Explanations

    html href and action attributes

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

    The main thing this neuron does is detect HTML anchor link references (the “href” attribute in <a> 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_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
    Some
    -0.97
    These
    -0.92
    出来ました
    -0.89
    Why
    -0.87
    Proč
    -0.87
    encie
    -0.86
    That
    -0.85
    Using
    -0.83
    の為
    -0.83
    Also
    -0.82
    POSITIVE LOGITS
     "../
    1.16
     '../
    1.03
    https
    1.02
    =#
    0.99
     ../
    0.98
     زي
    0.96
     \#
    0.95
     https
    0.94
     #
    0.94
    ="
    0.94
    Activations Density 0.006%

    No Known Activations