© 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. 10-GEMMASCOPE-RES-131K
    7. 19718
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    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_10/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
     Olivenöl
    -1.62
     muualla
    -1.58
    práv
    -1.57
    hodné
    -1.55
    lossians
    -1.55
     about
    -1.51
     attacc
    -1.50
     who
    -1.50
     mereka
    -1.49
     gunakan
    -1.46
    POSITIVE LOGITS
    :
    1.49
    -
    1.41
     for
    1.30
     молодой
    1.30
     ambos
    1.26
     itself
    1.24
     nasceu
    1.23
     communauté
    1.23
    えたら
    1.22
     respondeu
    1.21
    Activations Density 0.251%

    No Known Activations