© 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. 34853
    Prev
    Next
    INDEX
    Explanations

    comment markers

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

    This neuron detects the start of comments in source code (e.g. “/*”, “//”, “;;”, “--”, “##”).

    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
     však
    -1.17
    CÓ
    -1.01
    Kup
    -1.00
    hline
    -0.99
     диван
    -0.99
    куртка
    -0.96
    और
    -0.96
    写的
    -0.96
    neten
    -0.95
    यह
    -0.95
    POSITIVE LOGITS
     bubuk
    1.25
     beginning
    1.07
    楽しめる
    1.06
    修为
    1.05
     termurah
    1.03
     now
    1.02
     there
    1.02
    Even
    1.01
     commencing
    1.01
     versuchen
    0.98
    Activations Density 0.038%

    No Known Activations