© 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. 34-GEMMASCOPE-RES-131K
    7. 49725
    Prev
    Next
    INDEX
    Explanations

    HTML doctype declarations

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

    The neuron fires on URL fragments—particularly the “http://www.w3.org/…” namespace and similar link prefixes in HTML/XML headers.

    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
    cava
    -0.92
     deut
    -0.84
    phoned
    -0.80
    lexus
    -0.80
     feminino
    -0.77
    uesta
    -0.76
    beh
    -0.75
    樑
    -0.75
     legal
    -0.73
     welcomes
    -0.73
    POSITIVE LOGITS
     math
    1.34
     Math
    1.33
    MathML
    1.22
    Math
    1.11
    MATHEMAT
    1.02
    Maths
    0.97
     математи
    0.97
     mathematicians
    0.96
     maths
    0.96
     Mathematica
    0.96
    Activations Density 0.020%

    No Known Activations