© 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. 21813
    Prev
    Next
    INDEX
    Explanations

    past timereferences

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

    This neuron detects explicit temporal references to past intervals, especially “earlier” or “<number> years earlier” mentions.

    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
     rito
    -1.34
     is
    -1.33
     voyager
    -1.25
     dikt
    -1.23
     piaggio
    -1.22
     beholder
    -1.22
     puma
    -1.20
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.20
     dolom
    -1.20
     versace
    -1.19
    POSITIVE LOGITS
     dieser
    1.48
     cette
    1.48
     спросил
    1.46
     to
    1.44
     THE
    1.31
    supplied
    1.28
    谙
    1.28
    鈺
    1.28
     durante
    1.26
     mengatur
    1.23
    Activations Density 0.015%

    No Known Activations