© 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. 117122
    Prev
    Next
    INDEX
    Explanations

    trend or trends

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

    The neuron detects words relating to statistical reporting and data‐driven trends (e.g. “trend,” “increasing,” “current,” “determine,” “temporal”).

    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
    faqs
    -0.81
    
    -0.78
    hingga
    -0.77
     "|"
    -0.77
    tschaft
    -0.75
    ίδι
    -0.75
    lapses
    -0.73
     équi
    -0.73
    phoric
    -0.73
    rifice
    -0.73
    POSITIVE LOGITS
     trend
    6.56
     trends
    6.44
    trend
    4.97
     Trends
    4.91
    trends
    4.59
     Trend
    4.41
    Trends
    4.41
     тенден
    4.03
    Trend
    4.03
    趋势
    3.89
    Activations Density 0.087%

    No Known Activations