© 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. 10-GEMMASCOPE-RES-131K
    7. 43009
    Prev
    Next
    INDEX
    Explanations

    don't followed by verb

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

    The neuron fires on the substring “don,” most prominently at the start of the contraction “don’t.”

    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
    m
    -2.78
    c
    -2.45
    r
    -2.38
    嘚
    -2.31
    f
    -2.16
    a
    -2.14
    e
    -2.13
    籥
    -2.13
    or
    -2.13
     our
    -2.11
    POSITIVE LOGITS
    \
    2.31
    撷
    2.27
    {
    2.23
    ’.
    2.09
     concise
    2.06
    
    1.99
    
    1.96
    态度
    1.93
     waa
    1.88
     插图
    1.86
    Activations Density 0.003%

    No Known Activations