© 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. 55850
    Prev
    Next
    INDEX
    Explanations

    knowledge management and documents

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tableFuture
    -0.68
    ليات
    -0.68
    ланд
    -0.68
    Gog
    -0.67
     leased
    -0.67
    スマ
    -0.67
     VIP
    -0.67
    stdafx
    -0.67
     расход
    -0.66
    淸
    -0.66
    POSITIVE LOGITS
     Knowledge
    1.27
     knowledge
    1.23
     KM
    1.19
     SharePoint
    1.19
    Knowledge
    1.15
    KM
    1.09
     document
    1.05
    Document
    1.03
     Document
    1.03
     tacit
    1.02
    Activations Density 0.033%

    No Known Activations