© 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. 10-GEMMASCOPE-RES-131K
    7. 57467
    Prev
    Next
    INDEX
    Explanations

    time periods

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

    The neuron detects mentions of “time period” (numeric temporal spans) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鹟
    -1.96
     Like
    -1.93
     accommodates
    -1.89
     Despite
    -1.88
    というわけで
    -1.85
    льному
    -1.80
     trovano
    -1.76
    s
    -1.68
    Despite
    -1.66
     Even
    -1.64
    POSITIVE LOGITS
    の人に
    1.96
    🫃
    1.84
     pessoas
    1.75
     günstiger
    1.74
    他の
    1.74
    の方に
    1.73
     awe
    1.72
     estadounidenses
    1.72
     battles
    1.70
     océano
    1.70
    Activations Density 0.004%

    No Known Activations