© 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. 34-GEMMASCOPE-RES-131K
    7. 92546
    Prev
    Next
    INDEX
    Explanations

    yesterday and today

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

    The neuron strongly activates on sentence-ending full stops, i.e. periods that mark the ends of sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    бл
    -1.04
    doi
    -1.04
     都市
    -1.02
    现在的
    -0.96
     होने
    -0.95
     AUGUST
    -0.94
    isNaN
    -0.93
    winter
    -0.92
     NOVEMBER
    -0.92
    indd
    -0.92
    POSITIVE LOGITS
     yesterday
    10.25
    Yesterday
    6.72
     Yesterday
    6.47
    yesterday
    6.41
     last
    5.56
     вчера
    5.41
     today
    5.31
     gestern
    5.06
    昨天
    4.41
     ieri
    4.38
    Activations Density 0.451%

    No Known Activations