© 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. 73566
    Prev
    Next
    INDEX
    Explanations

    listing identifiers and definitions

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

    The neuron strongly activates on standalone numeric tokens (years, section or figure numbers, IDs, timestamps, etc.).

    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
     either
    -1.00
     extraordinary
    -0.88
     for
    -0.86
     entweder
    -0.84
     complicated
    -0.78
     what
    -0.78
    年前
    -0.77
     frantic
    -0.75
     would
    -0.74
     by
    -0.73
    POSITIVE LOGITS
     INTEGR
    0.96
    beitrag
    0.89
     Integr
    0.85
    统计
    0.81
     Integrate
    0.79
    Ⓨ
    0.78
     Sermons
    0.77
    kow
    0.77
     adams
    0.77
    voyer
    0.77
    Activations Density 0.000%

    No Known Activations