© 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. 22-GEMMASCOPE-RES-131K
    7. 129835
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on tokens containing the letter “x” (in any case) as part of identifiers or acronyms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    capital letters followed by other characters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    anthene
    -2.80
     including
    -2.50
     nearing
    -2.41
     despite
    -2.39
    ção
    -2.38
     because
    -2.36
     consisting
    -2.31
     That
    -2.31
     encompassing
    -2.31
     comprising
    -2.30
    POSITIVE LOGITS
     sont
    2.80
    s
    2.72
    𖣔
    2.48
    entikan
    2.38
     két
    2.30
     สุ
    2.30
     ก็
    2.28
     trois
    2.25
     บ้าน
    2.22
        
    2.22
    Activations Density 0.118%

    No Known Activations