© 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. 65436
    Prev
    Next
    INDEX
    Explanations

    monitors

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

    The neuron fires on technical hardware references—brand names, model numbers, and device specifications.

    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
    wallet
    -0.85
     Wallet
    -0.80
    Immune
    -0.78
     Immune
    -0.74
    SelectedIndex
    -0.73
     polymerase
    -0.73
    рами
    -0.71
    Wallet
    -0.71
    manuel
    -0.71
    ressee
    -0.70
    POSITIVE LOGITS
     monitor
    3.83
     monitors
    3.50
    monitor
    3.00
     Monitor
    2.92
    Monitor
    2.72
     Monitors
    2.66
     мони
    2.56
     monitores
    2.34
     MONITOR
    2.34
    MONITOR
    2.27
    Activations Density 0.092%

    No Known Activations