© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68897
    Prev
    Next
    INDEX
    Explanations

    HTML tags

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

    The neuron fires on the literal “<” characters that introduce 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
    が
    -1.15
    áneamente
    -1.02
     to
    -1.02
    そのため
    -1.02
     by
    -1.01
    によって
    -0.96
    にて
    -0.94
    見えます
    -0.94
    での
    -0.91
     extranjera
    -0.90
    POSITIVE LOGITS
     another
    1.39
     also
    1.31
     further
    1.14
     másik
    1.13
    flügel
    1.07
    為に
    1.07
     ulteriori
    1.06
    Another
    1.03
     camión
    1.02
    landais
    1.02
    Activations Density 0.002%

    No Known Activations