© 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. 60922
    Prev
    Next
    INDEX
    Explanations

    place names 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_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
     Corinthians
    -0.82
    σιν
    -0.79
    estos
    -0.77
     جز
    -0.75
    ҕ
    -0.74
     dettaglio
    -0.72
     Whoa
    -0.72
    CAPE
    -0.72
    ANSAS
    -0.71
     vlas
    -0.70
    POSITIVE LOGITS
     Hampshire
    0.77
     Winchester
    0.69
     Greenfield
    0.67
     Beatty
    0.66
     Fayette
    0.66
     Frat
    0.65
     Ate
    0.64
    Frat
    0.63
    tern
    0.63
    Wart
    0.63
    Activations Density 0.041%

    No Known Activations