© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11934
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    The neuron is detecting numeric digits (i.e. characters 0–9) in numerical sequences such as timestamps, IDs, dates, and other numbers.

    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
     as
    -1.93
     after
    -1.91
     without
    -1.73
     in
    -1.63
     could
    -1.62
     because
    -1.62
     focusing
    -1.61
     with
    -1.60
     at
    -1.59
     mostly
    -1.51
    POSITIVE LOGITS
    
    1.60
     différentes
    1.55
    蓠
    1.52
    傒
    1.48
     ayur
    1.43
    ⬈
    1.43
     allerlei
    1.41
     nieuwe
    1.40
     accompagner
    1.33
     Atención
    1.32
    Activations Density 0.041%

    No Known Activations