© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99468
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence applications

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

    The neuron fires on occurrences of the term “artificial intelligence” or its abbreviation “AI.”

    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
     plethora
    -2.30
    \
    -2.20
     ordeal
    -1.99
     k
    -1.93
     lounging
    -1.91
     exuberant
    -1.87
     sehr
    -1.83
     z
    -1.82
    ’，
    -1.80
     Adding
    -1.80
    POSITIVE LOGITS
     concorda
    2.36
     nuovi
    2.27
     aplicativos
    2.22
    CAUTIONS
    2.13
     après
    2.09
     alarme
    2.08
     Reſ
    2.05
    
    2.05
     dentista
    2.05
    ſſen
    2.05
    Activations Density 0.012%

    No Known Activations