© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10358
    Prev
    Next
    INDEX
    Explanations

    Georgia, Atlanta, universities

    np_acts-logits-general · gemini-2.5-flash-lite

    Coca-Cola Georgia Atlanta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chandigarh
    0.41
     Saskatoon
    0.41
     Chichester
    0.40
     Lombok
    0.40
    産
    0.39
     bác
    0.39
     Тыва
    0.39
     बुन्देलखण्ड
    0.39
    elni
    0.39
    ",[(
    0.38
    POSITIVE LOGITS
    Georgia
    2.03
     Georgia
    2.00
     Atlanta
    1.90
    Atlanta
    1.84
     Tbilisi
    1.59
     Georgian
    1.50
     UGA
    1.50
     georg
    1.48
    Georgian
    1.38
     Peachtree
    1.35
    Activations Density 0.143%

    No Known Activations