© 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. 86170
    Prev
    Next
    INDEX
    Explanations

    overnight events and duration

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

    The neuron is triggered by mentions of “overnight” (especially in the context of overnight shipping or time periods).

    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
    汌
    -3.09
    𖥧
    -2.66
    S
    -2.50
    {
    -2.42
     It
    -2.33
    
    -2.31
    沕
    -2.28
    W
    -2.25
    кой
    -2.22
     avec
    -2.17
    POSITIVE LOGITS
    摃
    2.45
     –
    2.44
    霂
    2.38
    神
    2.36
    The
    2.33
     alemanes
    2.30
    
    2.28
    緜
    2.25
    哒
    2.22
     japoneses
    2.20
    Activations Density 0.003%

    No Known Activations