© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14134
    Prev
    Next
    INDEX
    Explanations

    events occurring subsequently

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

    The neuron fires on descriptive words that lay out a sequence of events or phases in a narrative (i.e. chronology markers and verbs describing steps in time).

    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
     сейчас
    -1.24
     سابق
    -1.23
     sekarang
    -1.13
    前は
    -1.13
     предыду
    -1.11
     tidigare
    -1.08
    earlier
    -1.05
    Earlier
    -1.05
     पि
    -1.05
     précédents
    -1.04
    POSITIVE LOGITS
     subsequent
    2.42
     subsequently
    2.42
     later
    2.20
     soon
    2.08
     then
    1.95
     next
    1.91
     thereafter
    1.88
    その後
    1.80
     anschließend
    1.77
     Subsequently
    1.66
    Activations Density 0.055%

    No Known Activations