© 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. 34-GEMMASCOPE-RES-131K
    4. 6768
    Prev
    Next
    INDEX
    Explanations

    ancient and traditional civilization

    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
     historical
    -1.38
    historical
    -1.30
    Historical
    -1.26
     histórico
    -1.22
     истори
    -1.20
     sejarah
    -1.19
     Historical
    -1.18
    Historic
    -1.17
     Historically
    -1.14
     ancient
    -1.12
    POSITIVE LOGITS
     art
    1.26
     agriculture
    1.20
     architecture
    1.13
     trade
    1.11
     artwork
    1.07
     arts
    1.07
     Architecture
    1.06
     military
    1.05
     coinage
    1.04
     clothing
    1.03
    Activations Density 0.036%

    No Known Activations