© 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. 107546
    Prev
    Next
    INDEX
    Explanations

    country codes and URLs

    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
     Fortuna
    -0.72
     đấu
    -0.69
    applicazione
    -0.69
    客观
    -0.68
     Tuscany
    -0.67
     Garmin
    -0.67
    pixel
    -0.66
    Вес
    -0.66
    ERTE
    -0.66
    有一天
    -0.66
    POSITIVE LOGITS
     US
    2.20
     UK
    1.98
    US
    1.85
    UK
    1.74
     uk
    1.65
    uk
    1.44
     GB
    1.38
     en
    1.30
     USA
    1.26
    GB
    1.24
    Activations Density 0.118%

    No Known Activations