© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8174
    Prev
    Next
    INDEX
    Explanations

    Atlanta Georgia

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

    Georgia and Georgians

    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_53_width_65k_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
     Lombok
    0.56
    肝
    0.48
    SQLite
    0.47
     SQLite
    0.44
    ¦
    0.43
     XLSX
    0.43
     disgu
    0.42
     अभिषेक
    0.41
    渭
    0.41
    캥
    0.41
    POSITIVE LOGITS
     Georgia
    3.61
    Georgia
    3.56
     Atlanta
    3.11
    Atlanta
    3.02
     georg
    2.83
     Georgian
    2.78
    Georgian
    2.58
     Tbilisi
    2.55
     UGA
    2.39
     Грузии
    2.38
    Activations Density 0.144%

    No Known Activations