© 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. 85266
    Prev
    Next
    INDEX
    Explanations

    sending or transferring information

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

    The main thing this neuron does is detect mentions of sending or transmitting content (e.g. “send,” “sending,” “transmit,” “sendMessage,” “上传/发送”).

    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
    寕
    -2.67
    一九
    -1.98
    媜
    -1.95
    ౭
    -1.78
    也能
    -1.77
    橚
    -1.77
    linawan
    -1.66
    毋
    -1.66
    哙
    -1.66
    囯
    -1.65
    POSITIVE LOGITS
     to
    2.28
    瑧
    2.08
    謌
    2.06
    こんばん
    1.77
    鶿
    1.67
    そういえば
    1.64
    瞜
    1.63
    縂
    1.63
    谖
    1.61
    られて
    1.58
    Activations Density 0.005%

    No Known Activations