© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on words naming transportation modes and related transit infrastructure (e.g. cars, taxis, bike stations, bicycles).

    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
     IUCN
    0.56
    ந்தது
    0.55
    に関しては
    0.55
    ansion
    0.55
    此事
    0.53
     Diskussion
    0.52
     outra
    0.52
    棫
    0.52
    </table>
    0.52
     درسنا
    0.51
    POSITIVE LOGITS
    人们
    2.83
     people
    2.67
    人們
    2.61
     люди
    2.52
     mensen
    2.48
     людям
    2.47
     users
    2.44
     människor
    2.44
     insanlar
    2.36
     사람들이
    2.34
    Activations Density 3.666%

    No Known Activations