© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 614
    Prev
    Next
    INDEX
    Explanations

    operational service history

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

    The neuron is triggered by numeric tokens, especially dates, model or version numbers, and other numerical 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
    Ticks
    -0.75
     reprint
    -0.72
     суд
    -0.71
     preprint
    -0.70
     vọng
    -0.69
    iastical
    -0.68
    Ejec
    -0.66
    我一直
    -0.66
     motorcycles
    -0.66
     uusi
    -0.65
    POSITIVE LOGITS
     service
    2.34
    service
    1.83
     servicio
    1.59
    ervice
    1.51
    Service
    1.48
     Service
    1.47
     SERVICE
    1.35
     servizio
    1.34
     operational
    1.28
     служба
    1.23
    Activations Density 0.059%

    No Known Activations