© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 223
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to words denoting movement or progression (action verbs of “going,” “walking,” “turning,” etc.).

    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
     wobei
    0.19
     prilikom
    0.19
     ramach
    0.18
     ayant
    0.18
     establecida
    0.18
     yoki
    0.18
     pudi
    0.18
     및
    0.17
     kişinin
    0.17
     essendo
    0.17
    POSITIVE LOGITS
     into
    0.59
     down
    0.59
     back
    0.58
     out
    0.55
     up
    0.53
     away
    0.45
     BACK
    0.44
     ashore
    0.44
     forth
    0.43
     forward
    0.43
    Activations Density 1.182%

    No Known Activations