© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67600
    Prev
    Next
    INDEX
    Explanations

    sequence of events or time

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

    The neuron flags spans that are rich in temporal or scheduling information—dates, time‐order transitions, and event resumption or revival.

    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
    yAxis
    -0.90
    itez
    -0.85
    
    -0.83
     its
    -0.77
    ürger
    -0.76
    vā
    -0.74
     pasaba
    -0.74
    apia
    -0.73
    epochs
    -0.72
     APPELLANT
    -0.72
    POSITIVE LOGITS
     next
    1.68
     until
    1.17
     następ
    1.13
     ďal
    1.12
     další
    1.11
     بعدی
    1.10
    次は
    1.05
    Next
    1.04
     thereafter
    1.04
     infrequent
    1.02
    Activations Density 0.062%

    No Known Activations