© 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. 48014
    Prev
    Next
    INDEX
    Explanations

    English place names and regions

    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
    Coastal
    -0.79
     Coastal
    -0.76
    ibos
    -0.75
     estuary
    -0.74
     hören
    -0.73
     Winder
    -0.72
    ")));
    -0.72
    räger
    -0.70
     Felder
    -0.70
     Outbreak
    -0.70
    POSITIVE LOGITS
     Huddersfield
    0.94
     Tyrone
    0.85
    豸
    0.81
     Já
    0.77
     Gum
    0.74
    祁
    0.74
     Rough
    0.72
    Wort
    0.71
    Gum
    0.71
    üch
    0.71
    Activations Density 0.074%

    No Known Activations