© 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. 10-GEMMASCOPE-RES-131K
    7. 124167
    Prev
    Next
    INDEX
    Explanations

    years

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

    The neuron detects numeric tokens (counts, years, measurements, statistics, and decimal 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
     more
    -1.57
    -1.53
     falls
    -1.52
     was
    -1.50
     is
    -1.48
     un
    -1.42
     opens
    -1.41
     owns
    -1.38
     his
    -1.38
     own
    -1.38
    POSITIVE LOGITS
    there
    1.43
     között
    1.38
     otot
    1.35
     légiti
    1.30
     which
    1.28
     homoto
    1.27
    hộp
    1.24
     használat
    1.22
     exacer
    1.20
     emphat
    1.20
    Activations Density 0.052%

    No Known Activations