© 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. 147
    Prev
    Next
    INDEX
    Explanations

    This neuron lights up on references to specific geographic places (e.g. town, region, country names).

    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
    、
    0.49
    _
    0.37
    )
    0.36
    の
    0.35
    ،
    0.35
    ,
    0.34
    x
    0.32
    ，
    0.32
    ()
    0.32
    的
    0.31
    POSITIVE LOGITS
     waarbij
    0.75
     allowing
    0.71
     waardoor
    0.71
     जिसमें
    0.70
     whereupon
    0.69
     which
    0.69
     wobei
    0.68
     affording
    0.67
     vilket
    0.66
     necessitating
    0.66
    Activations Density 1.090%

    No Known Activations