© 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. 70265
    Prev
    Next
    INDEX
    Explanations

    receptor and channel function

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

    neurotransmitter receptors and ion channels in scientific text, especially GABA, AMPA, and NMDA receptors.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     trailer
    -0.71
    ProgressDialog
    -0.68
     mortgage
    -0.68
    glucose
    -0.67
     cabinet
    -0.67
    祓
    -0.66
    ambiguation
    -0.66
     acquisition
    -0.66
     capa
    -0.66
    oksi
    -0.65
    POSITIVE LOGITS
     subunit
    1.04
     receptor
    0.85
    states
    0.85
     pore
    0.82
     subunits
    0.82
    Etter
    0.80
     receptors
    0.80
    inose
    0.79
    benz
    0.78
    zación
    0.77
    Activations Density 0.191%

    No Known Activations