© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116267
    Prev
    Next
    INDEX
    Explanations

    place names with follow-up 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
     Krak
    -0.76
     跳
    -0.73
     Penang
    -0.72
    downloaded
    -0.70
    楚
    -0.70
     Baloch
    -0.69
    Plo
    -0.68
     Illa
    -0.68
     claw
    -0.66
     ТЕ
    -0.66
    POSITIVE LOGITS
     Hertfordshire
    1.69
     Watford
    1.11
    茨城
    1.02
     Hert
    0.99
     Edmonton
    0.86
     Sharjah
    0.77
     Hatfield
    0.77
     Luton
    0.76
     Lotus
    0.75
     współ
    0.75
    Activations Density 0.031%

    No Known Activations