© 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. 116383
    Prev
    Next
    INDEX
    Explanations

    html doctype declarations

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

    The neuron fires on the “w” and “3” tokens that occur together in W3C URLs (e.g. the “www.w3.org” parts of DOCTYPEs and XML namespaces).

    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
    restler
    -0.83
    였
    -0.81
     classico
    -0.79
    ContextCompat
    -0.77
    //{
    -0.75
     梦
    -0.75
     salita
    -0.74
    ليات
    -0.74
     drift
    -0.74
     ultima
    -0.73
    POSITIVE LOGITS
    org
    1.26
    Org
    1.03
    ORG
    0.94
     razones
    0.90
     období
    0.89
     škole
    0.86
     org
    0.86
     ORG
    0.85
     prostředí
    0.85
     Xs
    0.84
    Activations Density 0.007%

    No Known Activations