© 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. 83174
    Prev
    Next
    INDEX
    Explanations

    links after stylesheet or Q

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

    The neuron strongly activates on backslash characters (e.g. “\”) used in code comments or markup, especially in documentation 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
    }{*}{}
    -0.90
    第一章
    -0.90
    Waarom
    -0.86
    افية
    -0.84
    mẫu
    -0.78
     enim
    -0.77
     Cik
    -0.76
    İyi
    -0.76
    vede
    -0.76
     by
    -0.76
    POSITIVE LOGITS
     trois
    1.00
    multicolumn
    0.99
     mogli
    0.96
     comenz
    0.94
    multi
    0.92
     começ
    0.91
     MULT
    0.91
     MULTI
    0.85
     osserv
    0.82
     echter
    0.79
    Activations Density 0.001%

    No Known Activations