© 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. 10-GEMMASCOPE-RES-131K
    7. 84487
    Prev
    Next
    INDEX
    Explanations

    company names and technical terms

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

    The neuron is detecting numerical tokens (quantities, measurements, and other numbers) 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_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
    an
    -3.63
    ان
    -3.02
    1
    -2.92
    8
    -2.89
    4
    -2.77
    “
    -2.77
    7
    -2.61
    er
    -2.52
    e
    -2.50
    2
    -2.48
    POSITIVE LOGITS
    跸
    3.33
    sedown
    3.00
    
    2.95
    俛
    2.81
    
    2.81
    蒌
    2.80
    鹛
    2.78
    ultier
    2.78
    饜
    2.75
    秾
    2.73
    Activations Density 0.001%

    No Known Activations