© 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. 84191
    Prev
    Next
    INDEX
    Explanations

    activity of or status

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

    The neuron consistently activates on sequences of digits—i.e. numbers (years, version numbers, IDs) 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
    orch
    -0.78
    nees
    -0.76
    izzata
    -0.75
    lovers
    -0.74
     цветов
    -0.74
    kone
    -0.74
    isms
    -0.73
    elow
    -0.73
    wachs
    -0.73
    Elő
    -0.73
    POSITIVE LOGITS
     Activity
    1.02
    activity
    1.02
    Activity
    0.93
     activity
    0.89
     trackers
    0.85
    check
    0.83
    log
    0.80
     logs
    0.77
    criminator
    0.74
    ultat
    0.73
    Activations Density 0.025%

    No Known Activations