© 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. 102864
    Prev
    Next
    INDEX
    Explanations

    structured text and descriptions

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

    This neuron responds to structural boilerplate and metadata markers—things like indentation spaces, code‐behind or front‐matter keywords, DOCTYPE declarations, and other markup/configuration directives.

    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
     mahu
    -0.96
     bakso
    -0.89
    골
    -0.82
    мость
    -0.80
     després
    -0.79
     enzymes
    -0.79
    SNMP
    -0.79
    ᴺ
    -0.78
    充值
    -0.77
    町
    -0.77
    POSITIVE LOGITS
     HttpServlet
    0.91
     bụ
    0.90
     dormitorios
    0.88
    办理
    0.87
     witch
    0.81
    处理器
    0.81
    ותר
    0.80
     crib
    0.79
     firs
    0.77
    פים
    0.76
    Activations Density 0.001%

    No Known Activations