© 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. 34-GEMMASCOPE-RES-131K
    7. 867
    Prev
    Next
    INDEX
    Explanations

    nodding

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

    This neuron mainly activates on unusually long tokens (i.e. longer words or strings), with activation roughly scaling with token length.

    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
    叹了口气
    -1.11
    开口道
    -1.02
    轻声
    -1.00
    摇摇头
    -0.99
    摇了摇头
    -0.95
    见状
    -0.91
    笑了笑
    -0.90
    pyrene
    -0.83
     describir
    -0.80
     Schwar
    -0.79
    POSITIVE LOGITS
     nodded
    5.38
     nodding
    4.59
     nod
    4.56
     nods
    4.38
     Nod
    3.88
    nod
    3.80
    Nod
    3.66
     NOD
    2.77
     node
    2.56
    NOD
    2.45
    Activations Density 0.018%

    No Known Activations