© 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. 10-GEMMASCOPE-RES-131K
    4. 101545
    Prev
    Next
    INDEX
    Explanations

    Greek history and places

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

    The neuron is a detector for references to Greece or Greek‐related proper nouns (places, culture, and names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     GeoNames
    -1.34
     поэтому
    -1.32
     degust
    -1.29
     perig
    -1.24
     paradis
    -1.24
     automatica
    -1.23
     conflic
    -1.20
     suco
    -1.16
     resili
    -1.15
     トレ
    -1.15
    POSITIVE LOGITS
     they
    1.55
     standard
    1.28
    ↵
    1.27
    "}";
    1.26
     origin
    1.25
     example
    1.22
     Greece
    1.20
     podróż
    1.20
    Greece
    1.20
     person
    1.18
    Activations Density 0.033%

    No Known Activations