© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7091
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis in code

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

    Neuron 4 looks for closing‐parenthesis tokens in code—i.e. instances of “)” that end argument lists or function‐call parentheses.

    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
    </h2>
    -3.00
    هما
    -2.86
     продукти
    -2.84
    er
    -2.72
    悒
    -2.45
    堿
    -2.38
    蔼
    -2.34
    ၟ
    -2.33
    骋
    -2.33
    ে
    -2.33
    POSITIVE LOGITS
    </u>
    3.66
     
    3.58
    1
    3.31
    ')
    2.91
    </strong>
    2.86
    她
    2.63
    十分的
    2.39
    であれば
    2.38
    哪怕
    2.30
    依然
    2.27
    Activations Density 0.008%

    No Known Activations