© 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. 34667
    Prev
    Next
    INDEX
    Explanations

    opening tags or declarations

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

    The neuron detects structural metadata tokens—e.g. section titles, config keys, markup tags, and interface/type names that denote document structure.

    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
    PACS
    -0.76
    PRICE
    -0.71
     PRICE
    -0.71
    :[
    -0.66
    ăm
    -0.66
     chrys
    -0.65
     pojem
    -0.65
    🎀
    -0.65
    tadır
    -0.64
     pengalaman
    -0.64
    POSITIVE LOGITS
     خوا
    0.71
    Blazor
    0.70
     Ruff
    0.66
     유
    0.66
     Jung
    0.65
     Bologna
    0.64
     Et
    0.63
     Angry
    0.63
    istar
    0.62
    ติ
    0.62
    Activations Density 0.068%

    No Known Activations