© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65346
    Prev
    Next
    INDEX
    Explanations

    temporal sequencing of events

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

    The neuron is highly sensitive to the temporal adverb “after.”

    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
    zyj
    -1.05
     podnik
    -1.01
     bisogno
    -0.98
     demandé
    -0.98
     volgens
    -0.97
     locura
    -0.97
     zajíma
    -0.95
     Besonder
    -0.94
     besoin
    -0.94
     moeilijk
    -0.93
    POSITIVE LOGITS
     arrival
    0.91
    硬盘
    0.86
    lında
    0.85
    word
    0.84
     MINUTE
    0.83
    Rel
    0.82
    cti
    0.81
    common
    0.81
    ie
    0.80
    wel
    0.80
    Activations Density 0.047%

    No Known Activations