© 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. 60142
    Prev
    Next
    INDEX
    Explanations

    geochronology and dating

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

    The neuron is triggered by scientific numeric and measurement tokens—digits, figure references, isotope‐ratio numbers, and other technical numerical markers.

    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
    getClass
    -0.74
     once
    -0.74
    amed
    -0.71
    するように
    -0.71
     getTitle
    -0.69
    NANCY
    -0.68
    IRON
    -0.67
    chars
    -0.66
    뎅
    -0.65
     drawers
    -0.65
    POSITIVE LOGITS
    Dates
    0.88
     ages
    0.87
     age
    0.85
     Concordia
    0.84
     Picchu
    0.84
    bane
    0.82
     dates
    0.81
    dates
    0.81
    Pb
    0.80
     Pb
    0.80
    Activations Density 0.027%

    No Known Activations