© 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. 34-GEMMASCOPE-RES-131K
    7. 45598
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office products

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

    This neuron detects numeric version tokens (e.g. the digits in “Office 365”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     chờ
    -0.79
    としている
    -0.78
     celebró
    -0.77
    ého
    -0.74
    辛苦
    -0.73
    nges
    -0.73
    noh
    -0.72
     freut
    -0.72
    viesa
    -0.71
    亠
    -0.71
    POSITIVE LOGITS
     GCC
    0.77
     subscriptions
    0.77
     Ibn
    0.76
     Auctions
    0.75
     $\%$
    0.75
     Mural
    0.73
     subscription
    0.73
    gger
    0.72
     Jerez
    0.71
     Sperm
    0.70
    Activations Density 0.034%

    No Known Activations