© 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. 53854
    Prev
    Next
    INDEX
    Explanations

    time and punctuality

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

    This neuron activates on scheduling or timing cues—words and tokens that denote event times, starts, dates, and related temporal details.

    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
    比べ
    -0.81
    ски
    -0.77
    today
    -0.76
    ilas
    -0.75
    tivas
    -0.74
    خوب
    -0.74
    atmosphère
    -0.73
     thôi
    -0.71
    ammans
    -0.71
    ^{-\
    -0.71
    POSITIVE LOGITS
     exactly
    3.03
     punctual
    2.86
     punct
    2.86
     exact
    2.81
     precisely
    2.63
     precise
    2.44
    punct
    2.36
     prompt
    2.34
     Punct
    2.33
     sharp
    2.30
    Activations Density 0.035%

    No Known Activations