© 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. 22-GEMMASCOPE-RES-131K
    7. 13103
    Prev
    Next
    INDEX
    Explanations

    geographical locations and administrative divisions

    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_22/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
     πρ
    -1.17
    IpAddress
    -1.16
    mentes
    -1.02
     seront
    -0.96
     ſtate
    -0.95
     retos
    -0.94
    VALIDATE
    -0.93
     électrique
    -0.93
     months
    -0.93
     alcalde
    -0.91
    POSITIVE LOGITS
     όπου
    0.94
     in
    0.93
     aunque
    0.93
     stesse
    0.92
     Jedes
    0.91
    ittäin
    0.91
     hampir
    0.91
     Each
    0.90
     handen
    0.90
    cja
    0.90
    Activations Density 0.045%

    No Known Activations