© 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. 67637
    Prev
    Next
    INDEX
    Explanations

    air pollution and mortality

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

    mentions of air pollution in academic or technical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on numeric tokens containing a decimal point.

    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
     będziemy
    -1.02
     będę
    -1.00
     afectadas
    -1.00
     najwięks
    -0.99
     zawsze
    -0.99
    ing
    -0.99
     jeszcze
    -0.96
     mindig
    -0.96
     słucha
    -0.96
    V
    -0.95
    POSITIVE LOGITS
     morfo
    1.28
     anivers
    1.19
     conster
    1.14
     accessoire
    1.14
     luminos
    1.10
     frambo
    1.09
     publice
    1.07
     galer
    1.06
     garan
    1.05
     harmonie
    1.05
    Activations Density 0.000%

    No Known Activations