© 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. 44664
    Prev
    Next
    INDEX
    Explanations

    years and numbers

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

    The neuron activates on numerical tokens (years, multi-digit numbers, and decimals).

    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
     only
    -2.06
     it
    -1.59
     more
    -1.48
     other
    -1.45
     dozens
    -1.45
     this
    -1.43
     could
    -1.41
     countless
    -1.40
     remained
    -1.40
     as
    -1.39
    POSITIVE LOGITS
     všechny
    1.60
    specifically
    1.45
    ardige
    1.36
    
    1.36
     perles
    1.36
     ſch
    1.36
    Were
    1.34
     oock
    1.34
     والذي
    1.33
     gastronomía
    1.33
    Activations Density 0.118%

    No Known Activations