© 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. 22-GEMMASCOPE-RES-131K
    4. 98333
    Prev
    Next
    INDEX
    Explanations

    function or method parameters

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

    The neuron specifically fires on the punctuation and keywords of function definitions and calls—especially the opening parenthesis “(” and the function-name tokens that precede it.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     then
    -1.13
     contrat
    -1.08
    อื่น
    -1.07
    hasErrors
    -1.05
     even
    -1.05
     سایر
    -1.04
     such
    -1.03
     trattano
    -1.00
     航空
    -0.98
    ̣n
    -0.98
    POSITIVE LOGITS
    や
    1.31
     ganado
    1.15
    或
    1.13
    2
    1.10
     reveló
    1.09
     zulassen
    1.09
     dizzy
    1.09
     incríveis
    1.06
     یا
    1.05
     możesz
    1.05
    Activations Density 0.005%

    No Known Activations