© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1083
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on Russian tokens related to oil (нефть) terminology.

    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_24_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
     indiqu
    0.55
     savons
    0.55
     identifiable
    0.54
    elere
    0.52
    iót
    0.52
    ଟି
    0.52
    ᱗
    0.51
     yalnızca
    0.51
    rét
    0.50
    އ
    0.50
    POSITIVE LOGITS
    -
    0.63
     Ча
    0.58
    _
    0.56
    Фа
    0.53
    skaya
    0.52
    Видео
    0.51
    сть
    0.50
    ский
    0.50
    Ча
    0.50
    0.50
    Activations Density 0.000%

    No Known Activations