© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105501
    Prev
    Next
    INDEX
    Explanations

    comment syntax `*/` or closing tags `</`

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

    the string pattern "*/" which marks the end of multi-line comments in code or appears in file paths.

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

    The neuron strongly activates on the “*/” sequence that closes block-style comments.

    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
     IBOutlet
    -1.94
     pneu
    -1.90
     serán
    -1.86
    砗
    -1.85
    みたいです
    -1.84
    詒
    -1.84
    телем
    -1.83
    êque
    -1.82
    鰕
    -1.80
    陂
    -1.79
    POSITIVE LOGITS
    ’
    2.78
    with
    2.59
    2
    2.55
    u
    2.38
    ou
    2.36
    By
    2.28
     the
    2.28
    la
    2.22
    7
    2.17
     Importantly
    2.16
    Activations Density 0.016%

    No Known Activations