© 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. 13409
    Prev
    Next
    INDEX
    Explanations

    numbers in code snippets

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

    The neuron strongly activates on numeric literals (especially floating-point constants and other standalone numbers).

    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
     these
    -1.32
    下車
    -1.20
     ferramenta
    -1.17
    盉
    -1.12
     ६
    -1.12
     chegada
    -1.09
     ५
    -1.09
    parente
    -1.09
     atracción
    -1.08
     oração
    -1.07
    POSITIVE LOGITS
    ступили
    1.13
     '*',
    1.09
     bénévol
    1.07
    ∛
    1.07
    jarati
    1.05
    ведите
    1.04
     sortir
    1.01
     dimiliki
    0.98
    λους
    0.98
    繰り返
    0.95
    Activations Density 0.007%

    No Known Activations