© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on any form of the verb “walk” (e.g., walk, walked, walking).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the verb "walk" and its variants (walked, walking) when describing physical movement or motion.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of physical movement through space, especially walking and similar locomotion actions.

    oai_token-act-pair · gpt-5Triggered 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
     Diving
    0.61
     Passing
    0.59
    วิทยา
    0.57
     Squash
    0.56
     Passes
    0.56
     Dive
    0.56
     Nucleic
    0.56
    Dive
    0.55
     Chloride
    0.55
     Ab
    0.54
    POSITIVE LOGITS
     past
    0.86
     across
    0.84
     around
    0.80
    across
    0.78
     barefoot
    0.78
     вперед
    0.75
     backwards
    0.74
     gait
    0.74
    around
    0.73
     into
    0.72
    Activations Density 0.430%

    No Known Activations