© 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. 14703
    Prev
    Next
    INDEX
    Explanations

    time elapsed since last occurrence

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

    The neuron detects temporal references—words and numbers marking dates, time spans, or points in time (e.g. “after,” “back,” “since,” years, or other numeric time markers”).

    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
     first
    -1.48
     впервые
    -1.12
     πρώ
    -1.11
     pirm
    -1.11
     пър
    -1.09
     ersten
    -1.08
    แรก
    -1.06
     primeros
    -1.05
     primeiro
    -1.05
     beginning
    -1.05
    POSITIVE LOGITS
     last
    2.05
     آخرین
    1.48
    last
    1.39
    LAST
    1.38
    Last
    1.38
     dernière
    1.31
     último
    1.30
     dernier
    1.28
    最後に
    1.23
     getLast
    1.23
    Activations Density 0.046%

    No Known Activations