© 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. 34-GEMMASCOPE-RES-131K
    4. 81689
    Prev
    Next
    INDEX
    Explanations

    land, water, air, and soil

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

    The neuron primarily activates on numeric tokens (numbers and statistics).

    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
    Senegal
    -0.91
     onCreateView
    -0.89
     notched
    -0.88
     земли
    -0.88
     ом
    -0.87
    Գ
    -0.84
     さん
    -0.83
     terres
    -0.81
     Tuhan
    -0.81
     COFFEE
    -0.81
    POSITIVE LOGITS
     water
    1.30
     air
    1.22
     sky
    1.13
     buildings
    1.11
     oceans
    1.08
    建物
    1.07
     vegetation
    1.03
     animals
    1.00
     plants
    0.97
     airspace
    0.97
    Activations Density 0.057%

    No Known Activations