© 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. 10-GEMMASCOPE-RES-131K
    4. 29128
    Prev
    Next
    INDEX
    Explanations

    times and currencies

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

    The neuron fires on numeric date‐ and time‐stamp fragments (years, months, days, hours, minutes, AM/PM tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?
    -1.62
     maje
    -1.52
    
    -1.47
     anciennes
    -1.45
    ctory
    -1.45
    我的
    -1.44
     jugos
    -1.42
     humeur
    -1.41
    ।
    -1.41
    禩
    -1.41
    POSITIVE LOGITS
     or
    1.55
     continued
    1.45
     betreffenden
    1.44
     кошка
    1.41
     to
    1.39
     Beschluss
    1.39
    ocere
    1.34
    vestream
    1.34
     comienzan
    1.34
     for
    1.33
    Activations Density 0.128%

    No Known Activations