© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87062
    Prev
    Next
    INDEX
    Explanations

    cities, towns, and counties

    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
     in
    -1.35
     such
    -1.13
     more
    -1.02
     greatly
    -0.98
     not
    -0.98
     wildly
    -0.98
     because
    -0.96
     widely
    -0.95
     first
    -0.94
     at
    -0.93
    POSITIVE LOGITS
     town
    1.38
     city
    1.28
     City
    1.24
     étui
    1.18
     Town
    1.18
    town
    1.11
     obligator
    1.10
    再也
    1.09
     moderne
    1.05
     sûre
    1.04
    Activations Density 0.077%

    No Known Activations