© 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. 10-GEMMASCOPE-RES-131K
    7. 110646
    Prev
    Next
    INDEX
    Explanations

    Xth consecutive/straight/time (number)

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

    The neuron detects ordinal or sequence-related numeric phrases indicating a “nth time” or position (e.g. first, second, fourth, consecutive).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    踌
    -1.54
     engraçado
    -1.49
     jonge
    -1.48
     remercier
    -1.44
    部分を
    -1.43
     rév
    -1.41
     július
    -1.41
    诙
    -1.41
     offrir
    -1.40
     veren
    -1.40
    POSITIVE LOGITS
     before
    1.98
     support
    1.62
     out
    1.46
     without
    1.41
     used
    1.40
     had
    1.34
     until
    1.34
     helps
    1.32
     another
    1.30
     Before
    1.29
    Activations Density 0.037%

    No Known Activations