© 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. 34577
    Prev
    Next
    INDEX
    Explanations

    mechanical coupling and components

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

    This neuron detects technical specification data, especially numeric measurements and associated unit or parameter labels.

    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
    頃から
    -0.73
     cleverly
    -0.72
     Empfang
    -0.71
    āli
    -0.68
     chảy
    -0.65
    ዋ
    -0.64
     Vorder
    -0.64
     embassies
    -0.64
     chạm
    -0.63
    Contacts
    -0.63
    POSITIVE LOGITS
     Coupling
    1.05
     coupling
    1.03
     Frame
    0.94
     couplings
    0.89
    Frame
    0.81
     hypoch
    0.81
    FrameLayout
    0.80
     frame
    0.77
    sede
    0.77
    出力
    0.76
    Activations Density 0.029%

    No Known Activations