© 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. 60938
    Prev
    Next
    INDEX
    Explanations

    synaptic integration

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

    terms related to the integration, transition, or insertion of elements (especially in scientific or educational contexts).

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

    The neuron is triggered by dense, technical scientific prose—particularly detailed descriptions of adult‐born neuron generation and integration in the hippocampus.

    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
    Bailey
    -0.75
    alten
    -0.74
     کور
    -0.72
    جموع
    -0.71
    lee
    -0.69
    richlet
    -0.67
    occa
    -0.66
     backpack
    -0.66
     traded
    -0.65
    Glide
    -0.65
    POSITIVE LOGITS
     integration
    5.88
     Integration
    4.97
    integration
    4.94
    Integration
    4.81
     integrate
    4.59
     integrating
    4.31
     integrates
    4.03
    integrate
    4.03
     integración
    4.00
     integrations
    3.88
    Activations Density 0.060%

    No Known Activations