© 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. 22-GEMMASCOPE-RES-131K
    7. 95847
    Prev
    Next
    INDEX
    Explanations

    sequence or consequence

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

    The neuron is primarily triggered by numeric expressions—digits, counts, measures, and other quantity-related 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_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
     perpet
    -0.73
    袤
    -0.72
    ぜひ
    -0.72
    designs
    -0.71
    atai
    -0.71
     добраться
    -0.70
     rowIndex
    -0.69
    гают
    -0.69
     omission
    -0.69
     implica
    -0.69
    POSITIVE LOGITS
     then
    1.45
     kemudian
    1.20
    Then
    1.16
     THEN
    1.14
     subsequently
    1.13
     Затем
    1.11
     ensuite
    1.04
     następnie
    1.04
     later
    1.01
     luego
    1.01
    Activations Density 0.093%

    No Known Activations