© 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. 90164
    Prev
    Next
    INDEX
    Explanations

    Normandy places and cider

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

    The neuron strongly activates on numeric expressions—years, counts, measurements, and other number tokens.

    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
    metto
    -0.73
    Miami
    -0.70
     gestes
    -0.69
     Miami
    -0.68
     Catalan
    -0.65
     Puy
    -0.63
    gitlab
    -0.63
     Plantation
    -0.63
    enfants
    -0.63
    Explore
    -0.63
    POSITIVE LOGITS
     Normandy
    1.49
     Caen
    1.14
     Normandie
    1.02
     Rouen
    0.96
    NORM
    0.94
     ябло
    0.93
     Omaha
    0.91
     Cider
    0.90
     cider
    0.89
     Norman
    0.86
    Activations Density 0.021%

    No Known Activations