© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    between controlled adsorption

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

    The main thing this neuron does is detect numeric expressions (quantities, measurements, and other number tokens) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     deshalb
    -1.00
     deswegen
    -0.95
    פיה
    -0.95
     conducteur
    -0.94
     cedo
    -0.93
     religieuses
    -0.91
     تؤ
    -0.91
     gereken
    -0.91
     TVs
    -0.91
     dietro
    -0.90
    POSITIVE LOGITS
     diccionario
    0.99
    deepEqual
    0.93
    şağı
    0.90
    펜
    0.89
    ooled
    0.86
     コース
    0.85
    ḏ
    0.85
    别墅
    0.85
    vident
    0.84
     previous
    0.83
    Activations Density 0.032%

    No Known Activations