© 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. 90921
    Prev
    Next
    INDEX
    Explanations

    hours, time, date

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

    The neuron fires on numeric timestamps (dates or times) in logs or diff headers.

    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
     at
    -1.04
    }{*}{
    -0.88
    xlabel
    -0.87
     made
    -0.84
    exitRule
    -0.83
     begin
    -0.82
     can
    -0.81
     στην
    -0.81
     part
    -0.81
     Part
    -0.81
    POSITIVE LOGITS
     lendemain
    1.09
    adds
    0.97
     hours
    0.96
    igkeiten
    0.95
    ㍑
    0.93
     内衣
    0.90
    Contexto
    0.89
     ساعت
    0.88
    Ajouter
    0.88
    Agregar
    0.87
    Activations Density 0.010%

    No Known Activations