© 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. 84216
    Prev
    Next
    INDEX
    Explanations

    code syntax: html, css, javascript, java, latex

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

    This neuron responds to tokens that introduce or name high-level code or markup constructs—like declaration keywords (for, function, var), HTML tag names with attributes, CSS selectors, or LaTeX commands.

    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
     there
    -1.24
     this
    -1.18
     their
    -1.13
     its
    -1.05
    irà
    -1.01
     on
    -0.97
    غط
    -0.96
     там
    -0.95
    تاح
    -0.95
    するもの
    -0.94
    POSITIVE LOGITS
     marta
    1.06
     ekster
    1.05
     stili
    1.04
    😕
    1.02
     🥰
    1.02
    acular
    1.02
    TONY
    1.02
     suman
    1.01
     dolar
    1.01
     eut
    1.00
    Activations Density 0.072%

    No Known Activations