© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34886
    Prev
    Next
    INDEX
    Explanations

    code and markup declarations

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

    This neuron activates on tokens that are part of document markup or code syntax (e.g., include directives, XML/HTML tags, section markers).

    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
     to
    -1.41
     other
    -1.22
    other
    -1.13
    Other
    -1.10
     if
    -1.09
    อื่น
    -1.08
     Other
    -1.04
    其他
    -1.03
    Those
    -0.96
     those
    -0.94
    POSITIVE LOGITS
    utiliz
    1.21
     obicei
    1.17
     cubiertos
    1.17
    barrow
    1.12
     VERT
    1.12
    sorry
    1.12
    essentially
    1.12
     lagen
    1.10
     zustand
    1.08
    采用了
    1.07
    Activations Density 0.004%

    No Known Activations