© 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. 79886
    Prev
    Next
    INDEX
    Explanations

    past events or states

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

    The neuron fires on temporal/aspectual function words—especially auxiliaries (like “has”) and time-marking adverbs (e.g. “already,” “previously,” “last”)—that signal tense or sequence.

    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
     that
    -0.99
    кг
    -0.95
    mbitos
    -0.94
    ğiniz
    -0.91
    EndContext
    -0.91
     puissiez
    -0.90
    onimo
    -0.90
    ある
    -0.89
    ObjectContext
    -0.88
    Kaynakça
    -0.85
    POSITIVE LOGITS
     previous
    2.22
     previously
    2.00
     similar
    1.69
     earlier
    1.65
    previously
    1.62
     sebelumnya
    1.53
     предыду
    1.49
     precedente
    1.43
    Previously
    1.38
     similarly
    1.37
    Activations Density 0.055%

    No Known Activations