© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73760
    Prev
    Next
    INDEX
    Explanations

    file path inclusions

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

    The neuron fires on URL–style strings in HTML or script tag attributes (e.g. in src or href paths).

    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
    였다
    -0.91
    quois
    -0.85
    createTextNode
    -0.82
    Todos
    -0.79
    getAbsolutePath
    -0.79
    ่ง
    -0.72
    טר
    -0.71
     mathématiques
    -0.71
    ardless
    -0.69
     inalámb
    -0.69
    POSITIVE LOGITS
    includes
    1.30
     includes
    1.26
     images
    1.16
     include
    1.15
    images
    1.05
     templates
    1.03
    Includes
    1.02
    templates
    0.99
    include
    0.95
     themes
    0.94
    Activations Density 0.036%

    No Known Activations