© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron is detecting mentions of consular or diplomatic office titles (e.g. “Consulate General,” “consular”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to consulates and diplomatic offices.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to consular/diplomatic offices, roles, and services within governmental foreign-affairs contexts.

    oai_token-act-pair · gpt-5Triggered 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
    idCliente
    0.56
     free
    0.55
    }]
    0.54
    видно
    0.52
    све
    0.52
    示す
    0.51
    writeValue
    0.50
     sı
    0.50
     anses
    0.50
     contentLength
    0.50
    POSITIVE LOGITS
     紹介
    0.70
     使っ
    0.68
     今天
    0.67
     ఆర్థిక
    0.67
     ต้องการ
    0.63
     雨
    0.62
    MPs
    0.61
     ด้าน
    0.60
     Carleton
    0.59
    戀
    0.59
    Activations Density 0.002%

    No Known Activations