© 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. 82943
    Prev
    Next
    INDEX
    Explanations

    street names and location types

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron chiefly activates on proper nouns naming real‐world places—e.g. streets, schools, markets, parks, towns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     vitale
    -0.95
     incendio
    -0.93
    вної
    -0.90
    SHIRE
    -0.88
     herbes
    -0.84
     oes
    -0.83
     robuste
    -0.82
    श्लेषण
    -0.81
     klassi
    -0.81
     parlement
    -0.81
    POSITIVE LOGITS
     Road
    1.17
     Close
    1.06
     street
    0.98
     View
    0.98
     Farm
    0.96
     Crescent
    0.94
     surgery
    0.94
     road
    0.94
     Surgery
    0.94
     House
    0.93
    Activations Density 0.048%

    No Known Activations