© 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. 34-GEMMASCOPE-RES-131K
    7. 50285
    Prev
    Next
    INDEX
    Explanations

    xml, code, and mathematical notation

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

    This neuron targets encoded escape sequences in code or markup (e.g. “\uXXXX” escapes and HTML entity sequences like “,”).

    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
     auch
    -0.91
     kind
    -0.89
     and
    -0.86
     tudi
    -0.84
     in
    -0.83
     slim
    -0.80
     from
    -0.79
     die
    -0.78
     of
    -0.76
     id
    -0.76
    POSITIVE LOGITS
     ,
    1.20
    
    1.10
    ​,
    1.03
    
    0.95
     consommer
    0.93
    ,
    0.91
    (),
    0.91
    >,
    0.89
     .
    0.89
     $,
    0.88
    Activations Density 0.075%

    No Known Activations