© 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. 83456
    Prev
    Next
    INDEX
    Explanations

    international teams

    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
     Reykjavik
    -0.85
    tions
    -0.82
    リフォーム
    -0.78
    >\<
    -0.75
    qu
    -0.75
    pa
    -0.74
    Unix
    -0.74
    WHIT
    -0.73
     Verenig
    -0.72
    คู่
    -0.72
    POSITIVE LOGITS
     England
    2.53
     Ireland
    2.52
     Canada
    2.47
     Australia
    2.39
     Italy
    2.36
     India
    2.36
     Germany
    2.25
     Nigeria
    2.25
     USA
    2.22
     France
    2.20
    Activations Density 0.067%

    No Known Activations