© 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. 3745
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

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

    The neuron fires on occurrences of the French word “deux.”

    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
     Until
    -2.53
     Because
    -2.48
     Whether
    -2.44
     comienza
    -2.38
     เพราะ
    -2.19
     informací
    -2.19
     it
    -2.16
     Además
    -2.13
     groundwork
    -2.13
     tangle
    -2.11
    POSITIVE LOGITS
    蟶
    2.88
     been
    2.73
    饜
    2.70
    肏
    2.56
    戆
    2.56
    The
    2.53
    鼯
    2.52
    They
    2.47
    and
    2.47
    镲
    2.45
    Activations Density 0.001%

    No Known Activations