© 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. 102960
    Prev
    Next
    INDEX
    Explanations

    time indicators AM/PM

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

    The neuron detects the “PM” tokens in email‐header time stamps.

    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
     WHICH
    -2.09
    A
    -2.02
    
    -1.97
    庒
    -1.96
     proposées
    -1.88
    糶
    -1.85
     leão
    -1.85
     vuoi
    -1.81
     masina
    -1.80
     carcasa
    -1.76
    POSITIVE LOGITS
    .
    2.91
     of
    2.14
    \\
    2.05
    ↑↑↑</
    1.91
    selbe
    1.76
     When
    1.73
    潆
    1.70
    玙
    1.63
    ̖
    1.63
     Verständnis
    1.62
    Activations Density 0.012%

    No Known Activations