© 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. 76430
    Prev
    Next
    INDEX
    Explanations

    Sri Lanka, Colombo, Ceylon

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

    This neuron fires on date‐and‐location phrases—especially birth dates and birthplaces (e.g. parenthesized years and “born in [City, Country]”).

    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
     Cushion
    -0.79
    영화
    -0.76
    Precautionary
    -0.75
     体験
    -0.71
    tificates
    -0.71
     voorbeeld
    -0.71
     Phenomena
    -0.70
    acterium
    -0.70
    boro
    -0.70
    🍷
    -0.69
    POSITIVE LOGITS
     Colombo
    1.24
     Sri
    1.02
     Galle
    0.90
     SRI
    0.90
     Ceylon
    0.90
    Sri
    0.84
    titue
    0.83
    रिक
    0.79
     Lanka
    0.78
     Cinnamon
    0.77
    Activations Density 0.016%

    No Known Activations