© 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. 119101
    Prev
    Next
    INDEX
    Explanations

    Saint George, Barbados

    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
     because
    -0.78
     strengthen
    -0.74
    isticas
    -0.74
     фі
    -0.73
     Mayor
    -0.73
    URN
    -0.72
     enhance
    -0.69
    汕
    -0.69
     känna
    -0.69
     Ponce
    -0.69
    POSITIVE LOGITS
     Barbados
    1.89
    Barbados
    1.50
     Barba
    1.32
     Baj
    1.30
    Rihanna
    1.05
    🇧
    1.05
    Baj
    1.03
     baj
    0.99
     Rihanna
    0.97
    barb
    0.90
    Activations Density 0.005%

    No Known Activations