© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98224
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    The neuron is looking for time stamps (numbers separated by colons indicating hours and minutes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     leão
    -1.09
     escritório
    -1.06
    Ļ
    -1.05
     that
    -1.02
    lioni
    -1.01
     синий
    -0.98
     bluse
    -0.96
    achelor
    -0.94
    сама
    -0.94
     in
    -0.92
    POSITIVE LOGITS
     الفلك
    0.94
    的目光
    0.94
     Their
    0.93
     Когда
    0.88
     تكون
    0.87
    el
    0.87
    Accreditation
    0.86
     الأف
    0.85
    料金
    0.85
     follicles
    0.85
    Activations Density 0.043%

    No Known Activations