© 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. 9722
    Prev
    Next
    INDEX
    Explanations

    numbers or Roman numerals

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

    The neuron activates on numeric tokens—especially multi‐digit numbers—marking references, figure numbers, parts, or measurements.

    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
    Adicionar
    -1.21
     kré
    -1.21
    ҵ
    -1.20
     interessantes
    -1.19
     kapac
    -1.18
     querían
    -1.18
     kateg
    -1.16
     tristes
    -1.16
     atlet
    -1.15
     camiset
    -1.14
    POSITIVE LOGITS
    u
    1.25
    n
    1.23
    c
    1.04
    O
    1.03
    N
    1.03
    ra
    1.03
    l
    1.02
    b
    1.00
    ou
    0.99
    v
    0.99
    Activations Density 0.037%

    No Known Activations