© 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. 10-GEMMASCOPE-RES-131K
    7. 102015
    Prev
    Next
    INDEX
    Explanations

    shaking, trembling, shivering

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

    The neuron activates on words referring to involuntary shaking or trembling motions.

    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
     aching
    -1.70
    鸰
    -1.66
    ↵
    -1.65
     sufrimiento
    -1.64
     gloom
    -1.63
     zincir
    -1.60
     sonrası
    -1.59
     acuario
    -1.59
     excruciating
    -1.59
     raging
    -1.58
    POSITIVE LOGITS
    桫
    1.66
     are
    1.62
     the
    1.51
    腠
    1.47
    ialmente
    1.44
    vantaged
    1.41
     guz
    1.39
     tokopedia
    1.35
     hawa
    1.35
    CopyTo
    1.34
    Activations Density 0.006%

    No Known Activations