© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48302
    Prev
    Next
    INDEX
    Explanations

    temperate and subtropical climates

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

    The neuron activates on ecological habitat descriptors—adjectives naming climate or vegetation zones (e.g. “subtropical,” “tropical,” “moist,” “lowland,” “temperate”).

    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
    奩
    -2.08
    尨
    -1.98
     nebst
    -1.94
     ་
    -1.92
     вернулся
    -1.82
    僦
    -1.77
    coupled
    -1.75
    
    -1.73
    丅
    -1.72
    …’
    -1.67
    POSITIVE LOGITS
    0
    2.38
     if
    2.34
    s
    2.28
     During
    2.23
     besonders
    1.98
     When
    1.93
     >
    1.91
     both
    1.88
     intensely
    1.86
     Because
    1.82
    Activations Density 0.012%

    No Known Activations