© 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. 34625
    Prev
    Next
    INDEX
    Explanations

    neighborhoods and districts

    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
     santuario
    -0.89
    RECT
    -0.79
    公立
    -0.78
    mejores
    -0.76
     Campeonato
    -0.76
    downtown
    -0.76
    śni
    -0.75
    Iglesia
    -0.73
     casas
    -0.73
    合併
    -0.71
    POSITIVE LOGITS
     фильтр
    0.95
     contempor
    0.91
     tram
    0.88
     EXPO
    0.86
     facultad
    0.84
     shipyard
    0.84
    novo
    0.83
     subway
    0.83
     neighborhood
    0.82
     peripheral
    0.82
    Activations Density 0.064%

    No Known Activations