© 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. 91281
    Prev
    Next
    INDEX
    Explanations

    sensory system processing

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

    neuron that activates for terms related to sensory systems, particularly auditory, visual, and somatosensory cortical regions.

    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
    ＇
    -0.82
    ائف
    -0.79
    즌
    -0.77
    بوط
    -0.76
     sound
    -0.76
    eltjes
    -0.76
    mander
    -0.75
    роде
    -0.75
    購物
    -0.75
    ciptakan
    -0.75
    POSITIVE LOGITS
     system
    1.17
     input
    1.04
     System
    0.92
     processing
    0.90
    system
    0.88
     inputs
    0.86
     النظام
    0.84
     evoked
    0.79
     Input
    0.78
    蕾
    0.77
    Activations Density 0.105%

    No Known Activations