© 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. 22-GEMMASCOPE-RES-131K
    4. 592
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The neuron detects numeric tokens used in dates or timestamps (e.g. years, months, days, and time codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    despite
    -1.38
     its
    -1.26
    扌
    -1.20
     apesar
    -1.18
     communiquer
    -1.18
    )}
    
    -1.17
     satisfaire
    -1.14
    during
    -1.13
    gée
    -1.09
     lustige
    -1.09
    POSITIVE LOGITS
    Every
    1.03
    ! 
    1.01
     rudimentary
    1.00
    Other
    0.98
    Those
    0.98
    Some
    0.98
     horribly
    0.98
    Bjs
    0.97
     сейчас
    0.96
     был
    0.96
    Activations Density 0.273%

    No Known Activations