© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92892
    Prev
    Next
    INDEX
    Explanations

    insulating glass panes

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

    The neuron strongly activates on highly technical patent‐style descriptions of insulated multi‐layer glass panels or glazing units.

    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
    ่อน
    -0.77
     creadores
    -0.73
    开门
    -0.73
    ッパー
    -0.71
    epoxy
    -0.69
    食べた
    -0.69
     Volu
    -0.68
    asjoner
    -0.67
    ጌ
    -0.66
     asientos
    -0.66
    POSITIVE LOGITS
     insulating
    1.19
    DOUBLE
    1.16
     double
    1.16
     двой
    1.13
     glass
    1.13
     glazing
    1.03
     argon
    1.01
    double
    1.01
     insulated
    0.96
     triple
    0.96
    Activations Density 0.016%

    No Known Activations