© 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. 60471
    Prev
    Next
    INDEX
    Explanations

    bridge names and structures

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

    The neuron activates on any token containing the substring “bridge,” marking occurrences of “Bridge” in names, places, code identifiers, etc.

    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
    Bonjour
    -0.89
    Смотрите
    -0.88
    Stuttgart
    -0.86
     he
    -0.84
     mes
    -0.80
    瘢
    -0.80
    न
    -0.79
     Erfindung
    -0.79
    Lịch
    -0.79
     каждом
    -0.78
    POSITIVE LOGITS
     bridge
    1.24
    🌉
    1.20
     crossing
    1.10
    crossing
    1.10
     Bridge
    1.09
     桥
    1.06
     Brücken
    1.05
    bridge
    1.05
     spanning
    1.01
    quelize
    0.98
    Activations Density 0.013%

    No Known Activations