© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104306
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The neuron fires on numeric tokens (especially multi‐digit numbers and decimals) in tables or data outputs.

    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
    −/−
    -1.67
    They
    -1.52
    ază
    -1.39
     wenigstens
    -1.37
     آن‌ها
    -1.35
    /
    
    -1.32
    ∈
    -1.32
    いいのか
    -1.29
    Недоліки
    -1.29
     They
    -1.29
    POSITIVE LOGITS
     by
    1.36
     any
    1.36
     and
    1.33
    daun
    1.30
     tocando
    1.23
     as
    1.18
    梦见
    1.18
     seguido
    1.16
     What
    1.13
     exquisitely
    1.13
    Activations Density 0.073%

    No Known Activations