© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4331
    Prev
    Next
    INDEX
    Explanations

    programming and technical questions

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

    This neuron fires on tokens found in code license and copyright header blocks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Synchronized
    -0.83
    ляют
    -0.81
     gezicht
    -0.80
    loja
    -0.79
    دارة
    -0.78
    基本的に
    -0.75
    )._
    -0.75
    nerstag
    -0.73
     Wett
    -0.72
    ጎ
    -0.72
    POSITIVE LOGITS
     gibt
    0.85
    ーン
    0.83
    textColor
    0.82
     تیم
    0.77
    testers
    0.75
    場は
    0.73
     Delight
    0.73
    masked
    0.72
     menu
    0.72
     тон
    0.71
    Activations Density 0.000%

    No Known Activations