© 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. 11060
    Prev
    Next
    INDEX
    Explanations

    EXception. EXpose. Explain

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

    the two-letter prefix "EX" in technical or formal contexts, particularly in code, technical documentation, and product identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on occurrences of the uppercase letter sequence “EX.”

    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
     
    -3.02
    o
    -2.78
     For
    -2.75
     ehemaligen
    -2.69
     It
    -2.64
     Hoping
    -2.64
     Already
    -2.56
     Neither
    -2.55
     Either
    -2.53
     penchant
    -2.53
    POSITIVE LOGITS
     urat
    3.06
    珰
    3.05
    鼍
    2.88
    鮡
    2.88
    傩
    2.86
    涠
    2.81
    祧
    2.75
    牐
    2.75
     miljoner
    2.72
    蠊
    2.63
    Activations Density 0.004%

    No Known Activations