© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57000
    Prev
    Next
    INDEX
    Explanations

    action potential

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

    references to action potentials and electrical activity in scientific/medical papers about neurophysiology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is looking for mentions of electrophysiological membrane events—especially “action potentials” and related voltage changes (depolarization/hyperpolarization).

    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
    andr
    -0.88
     getSession
    -0.78
    волю
    -0.75
    astrar
    -0.74
     manly
    -0.73
    TagMode
    -0.69
     progressBar
    -0.67
     요청
    -0.67
    ченные
    -0.66
    Dimensões
    -0.66
    POSITIVE LOGITS
     potential
    4.41
     potentials
    4.38
    potential
    3.92
    Potential
    3.84
     Potential
    3.78
     потен
    3.42
     POTENTIAL
    2.98
     potencial
    2.88
     potenciales
    2.67
     Pot
    2.58
    Activations Density 0.109%

    No Known Activations