© 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. 35666
    Prev
    Next
    INDEX
    Explanations

    microsoft office related applications

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

    The neuron flags mentions of Microsoft Office products, services, and related document formats.

    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
    cterms
    -1.27
    isling
    -1.20
     tenían
    -1.20
    不错
    -1.16
     anglès
    -1.14
    踵
    -1.12
     ETH
    -1.11
    }=
    -1.11
    netics
    -1.11
     balanceOf
    -1.10
    POSITIVE LOGITS
    such
    1.42
    气势
    1.27
     rubrique
    1.18
     Such
    1.16
     possibilité
    1.16
     accompanies
    1.16
    势力
    1.15
     rhinoceros
    1.15
     imposes
    1.14
    当即
    1.14
    Activations Density 0.052%

    No Known Activations