© 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. 22-GEMMASCOPE-RES-131K
    7. 66574
    Prev
    Next
    INDEX
    Explanations

    Meanwhile, otherwise, elsewhere

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

    The neuron fires on named entities—especially place names, people’s names, and other proper nouns.

    oai_token-act-pair · o4-miniTriggered 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
     when
    -1.23
     after
    -1.02
     now
    -1.02
     ahora
    -1.01
     before
    -0.96
     sekarang
    -0.96
     después
    -0.95
     теперь
    -0.94
    今は
    -0.87
     both
    -0.85
    POSITIVE LOGITS
    Meanwhile
    2.34
     Meanwhile
    2.02
     meanwhile
    1.98
     meantime
    1.81
     elsewhere
    1.44
    Sementara
    1.44
    Mientras
    1.33
     sedang
    1.31
    busy
    1.17
    Elsewhere
    1.17
    Activations Density 0.055%

    No Known Activations