© 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. 34531
    Prev
    Next
    INDEX
    Explanations

    titles namesJoseph RadetzkyGovernor ofKing PōmareFrederick VII

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

    This neuron detects 4-digit year numbers (dates) in the text.

    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
     eighteenth
    -0.80
     phép
    -0.67
    quants
    -0.66
     детям
    -0.65
     wireless
    -0.65
     samochod
    -0.64
    thique
    -0.64
     arbitrary
    -0.64
    shadowColor
    -0.63
     Leinwand
    -0.63
    POSITIVE LOGITS
     Crimean
    1.45
     cholera
    0.89
     Whig
    0.87
    咸
    0.85
     Sardin
    0.84
    Victorian
    0.84
    רן
    0.82
     Crimea
    0.80
    Revue
    0.80
     Victorian
    0.79
    Activations Density 0.112%

    No Known Activations