© 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. 22-GEMMASCOPE-RES-131K
    7. 26594
    Prev
    Next
    INDEX
    Explanations

    tokens after comments or special characters

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

    The neuron activates on words appearing in code comments (text following “//”), detecting comment content rather than actual code.

    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
     betek
    -1.05
     satisfacer
    -1.02
     nadru
    -0.99
    München
    -0.99
     bordados
    -0.97
     offrent
    -0.95
    Baking
    -0.94
    horloge
    -0.94
    Bounding
    -0.93
     họ
    -0.91
    POSITIVE LOGITS
     for
    1.82
    用来
    1.34
     used
    1.27
    สำหรับ
    1.04
     später
    1.03
     will
    0.99
    ที่จะ
    0.99
    irà
    0.99
     to
    0.95
     digunakan
    0.95
    Activations Density 0.014%

    No Known Activations