© 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. 117324
    Prev
    Next
    INDEX
    Explanations

    transparent electrodes

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

    The neuron strongly activates on chemical material terms—especially element symbols, compound names, and polymer/film identifiers.

    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
    issors
    -0.77
    notice
    -0.71
    phism
    -0.71
    ressor
    -0.71
    endish
    -0.70
     newState
    -0.70
    podes
    -0.70
    Джере
    -0.69
    asim
    -0.68
     ifade
    -0.68
    POSITIVE LOGITS
     transparent
    1.37
     Transparent
    1.31
    Transparent
    1.26
     прозра
    1.13
    transparent
    1.04
     transparente
    0.96
     Raz
    0.93
    透明
    0.91
     Hunts
    0.89
     Hole
    0.88
    Activations Density 0.070%

    No Known Activations