© 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. 10-GEMMASCOPE-RES-131K
    7. 118817
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "a"

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

    The neuron is primarily triggered by standalone uppercase “A” tokens (the single-letter article “A”).

    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
    O
    -2.98
    W
    -2.86
     excessively
    -2.84
    Q
    -2.80
     or
    -2.75
    U
    -2.67
    J
    -2.66
     superbly
    -2.64
    in
    -2.64
    X
    -2.59
    POSITIVE LOGITS
    ⇴
    2.45
    eſ
    2.45
     ravaged
    2.41
    
    2.39
    憷
    2.38
    despite
    2.34
    mbgg
    2.31
    :”
    2.30
    毟
    2.28
     ส์
    2.19
    Activations Density 0.049%

    No Known Activations