© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2741
    Prev
    Next
    INDEX
    Explanations

    The neuron detects words that describe physical movement or motion (e.g. traveling, moving, traversing, riding, fumble around).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    建成
    0.58
    }^{-}$
    0.57
     oncoming
    0.52
     hazırl
    0.52
     بالکل
    0.51
    监
    0.50
    堊
    0.50
    inflate
    0.49
     ଶ
    0.49
    atsuki
    0.49
    POSITIVE LOGITS
     roaming
    2.03
     wandering
    1.99
     wander
    1.94
     roam
    1.93
    移動
    1.85
     wanders
    1.84
     wandered
    1.81
     roving
    1.80
     이동
    1.70
    移动
    1.67
    Activations Density 1.088%

    No Known Activations