© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    coastal places and names

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

    The neuron fires on capitalized place names and numeric tokens—i.e. geographic proper nouns and numbers.

    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
    清洗
    -0.73
    лий
    -0.70
     National
    -0.69
     Toh
    -0.68
    abilirsiniz
    -0.68
     prospects
    -0.67
    ں
    -0.67
     Monats
    -0.66
    مساعدة
    -0.66
     возраст
    -0.65
    POSITIVE LOGITS
     fatti
    0.78
     кусо
    0.75
     discí
    0.73
    omans
    0.70
     époque
    0.69
     étroite
    0.69
     Accra
    0.68
    はずです
    0.68
     compétition
    0.68
    лід
    0.68
    Activations Density 0.040%

    No Known Activations