© 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. 34-GEMMASCOPE-RES-131K
    7. 91627
    Prev
    Next
    INDEX
    Explanations

    specific times

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

    This neuron detects temporal-location prepositions (e.g. “at,” “from,” “around”) that introduce dates or times.

    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
    mathrm
    -1.56
     twenties
    -1.23
     other
    -1.23
    “…”
    -1.21
     dozens
    -1.19
     not
    -1.13
     long
    -1.13
     ~$
    -1.12
     older
    -1.12
     didn
    -1.12
    POSITIVE LOGITS
     noon
    1.30
     pourront
    1.14
     
    1.13
     humeur
    1.13
     étend
    1.13
    📁
    1.10
     logiciels
    1.07
     verspre
    1.07
     gånger
    1.05
     fidé
    1.05
    Activations Density 0.024%

    No Known Activations