© 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. 73037
    Prev
    Next
    INDEX
    Explanations

    looking for question or greeting

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

    The neuron specifically detects occurrences of the “src” attribute in markup (e.g. HTML/XML 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
     if
    -2.08
     to
    -1.97
     for
    -1.93
     have
    -1.88
     because
    -1.81
     provide
    -1.80
     get
    -1.80
     their
    -1.74
     allow
    -1.70
     give
    -1.70
    POSITIVE LOGITS
    鸶
    1.94
    
    1.62
    unfortunately
    1.61
     uniquement
    1.58
    usually
    1.57
     exceptionally
    1.52
    hundreds
    1.51
    commonly
    1.51
     marvelous
    1.50
    mainly
    1.49
    Activations Density 0.000%

    No Known Activations