© 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. 84743
    Prev
    Next
    INDEX
    Explanations

    to X or not to X

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

    This neuron is specialized to detect parts of web addresses and related URL syntax (e.g. “http,” “www,” “.com,” “://,” domain/path tokens).

    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
     брон
    -0.80
     ロール
    -0.76
    اریخ
    -0.75
    uttered
    -0.71
     Terra
    -0.71
    役所
    -0.71
     Altstadt
    -0.70
     stirred
    -0.69
    Looking
    -0.67
    chemistry
    -0.67
    POSITIVE LOGITS
     Hamlet
    1.50
    Hamlet
    1.47
    Denmark
    1.12
     Denmark
    1.09
     acteurs
    0.96
     Ophelia
    0.94
     Claudius
    0.93
    UNC
    0.92
    Casper
    0.91
     Munster
    0.86
    Activations Density 0.003%

    No Known Activations