© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47732
    Prev
    Next
    INDEX
    Explanations

    christmas lights illumination

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

    The neuron strongly activates on date‐ and time‐stamp elements (day names, month/day numbers, times) and associated byline metadata in a news article header.

    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
    有两个
    -0.93
     sunny
    -0.90
    тивные
    -0.84
     Spring
    -0.82
     grey
    -0.82
    阳光
    -0.82
     today
    -0.81
     painful
    -0.80
    Spring
    -0.79
     солне
    -0.79
    POSITIVE LOGITS
     lights
    1.83
     illumination
    1.71
     lighting
    1.70
     illumin
    1.47
     illuminated
    1.44
     ilumin
    1.41
     Lights
    1.38
    lights
    1.37
     lighted
    1.36
    Lights
    1.36
    Activations Density 0.022%

    No Known Activations