© 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. 80774
    Prev
    Next
    INDEX
    Explanations

    cortical inhibitory interneurons and layers

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

    neurological and brain-related terminology, especially relating to neurons, synapses, and brain structures.

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

    The neuron selectively activates on domain‐specific neuroscience terminology—especially anatomical brain regions, cell types, and related technical nouns.

    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
    汀
    -0.81
    стик
    -0.79
    腊
    -0.78
    Ах
    -0.77
    dov
    -0.74
     Draco
    -0.73
     Humor
    -0.72
    Obrázky
    -0.72
     radish
    -0.71
     büyü
    -0.71
    POSITIVE LOGITS
     Layer
    0.95
     layer
    0.84
    Layer
    0.81
    层
    0.79
     inhibitory
    0.78
     laminar
    0.75
     LAYER
    0.75
     inhibition
    0.75
     laminate
    0.75
     хол
    0.75
    Activations Density 0.183%

    No Known Activations