© 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. 10-GEMMASCOPE-RES-131K
    7. 103033
    Prev
    Next
    INDEX
    Explanations

    timezone or Rim fire

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

    The neuron detects occurrences of the term “timezone” (and closely related parameter names) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    al
    -3.13
    "
    -3.02
    s
    -2.92
    ...
    -2.86
     
    -2.64
    ли
    -2.50
    很好的
    -2.42
     the
    -2.27
    有點
    -2.25
    的
    -2.19
    POSITIVE LOGITS
    鈇
    3.48
    咴
    3.17
    
    3.13
    葑
    3.02
    逯
    2.98
    ⬯
    2.97
    Ꭳ
    2.91
    
    2.89
    geſ
    2.81
    晄
    2.77
    Activations Density 0.005%

    No Known Activations