© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38307
    Prev
    Next
    INDEX
    Explanations

    Singaporean places and institutions

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

    The neuron fires on multi‐word, title‐style proper names (especially institutional or organizational names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns and institutional names, particularly those related to Singapore organizations, schools, and people.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to Singapore-specific entities—proper nouns for its institutions, places, organizations, and people

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ときの
    -1.10
    Kira
    -1.07
    Encyclo
    -1.05
     penjara
    -1.02
     asesinato
    -1.02
    鏊
    -1.01
    Melan
    -1.01
     muere
    -1.00
     not
    -1.00
     Dictionnaire
    -0.99
    POSITIVE LOGITS
     Singapore
    1.11
    Singapore
    1.09
     personnalisés
    1.08
    анг
    1.07
    ENG
    1.07
     rhinoceros
    1.05
     preços
    1.02
    ↵↵↵
    1.01
    Enjoy
    1.00
    offsetWidth
    0.98
    Activations Density 0.028%

    No Known Activations