© 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. 8850
    Prev
    Next
    INDEX
    Explanations

    russia and soviet union

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on named‐entity tokens—proper nouns (people, places, organizations) and numeric/date strings—marking mentions of specific entities.

    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
    芊
    0.88
    台湾
    0.79
     JavaBeans
    0.79
     Productos
    0.77
    Ghana
    0.76
     जयपुर
    0.76
    马来
    0.76
    Alumno
    0.75
    骢
    0.75
     exámenes
    0.74
    POSITIVE LOGITS
     Russian
    3.19
     Moscow
    2.91
    Russian
    2.88
     Russia
    2.84
     Russians
    2.80
    Russia
    2.61
     russian
    2.59
    Moscow
    2.56
    ロシア
    2.55
     Kremlin
    2.52
    Activations Density 0.357%

    No Known Activations