© 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. 48222
    Prev
    Next
    INDEX
    Explanations

    movement

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

    The main thing this neuron does is detect mentions of movement or motion.

    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
    0
    -2.02
    as
    -1.90
    which
    -1.86
    for
    -1.82
    需要
    -1.78
    including
    -1.73
    如果不
    -1.70
     ト
    -1.67
    T
    -1.66
    2
    -1.66
    POSITIVE LOGITS
    汌
    2.45
    噲
    2.36
    และ
    2.19
    橦
    2.08
     begann
    2.08
    垌
    2.08
    Odpovědět
    2.06
    砭
    2.02
     și
    1.98
    炱
    1.96
    Activations Density 0.110%

    No Known Activations