© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49530
    Prev
    Next
    INDEX
    Explanations

    transaction isolation level

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

    The neuron specializes in spotting four‐digit version or year numbers (e.g. “2014”).

    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
     Mulligan
    -0.73
    sov
    -0.71
    APIC
    -0.71
     男孩
    -0.70
     한국
    -0.69
     GSP
    -0.69
     electrolytes
    -0.69
     inadequacy
    -0.69
     sporad
    -0.68
    bonus
    -0.68
    POSITIVE LOGITS
     reader
    1.01
    upgrade
    0.98
     readers
    0.97
    reader
    0.93
    readers
    0.90
     upgrade
    0.89
     upgrading
    0.86
     Inno
    0.78
     Reader
    0.78
     ghosts
    0.77
    Activations Density 0.027%

    No Known Activations