© 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. 10303
    Prev
    Next
    INDEX
    Explanations

    political party

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

    The main thing this neuron does is detect numeric expressions (numbers, dates, ordinals, and related numeric tokens).

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

    political party names and organizational affiliations.

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

    mentions of political parties and organizations, including their officials, committees, and formal meetings or conferences.

    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
     Hawking
    0.59
     HttpServlet
    0.57
     francs
    0.57
     출연
    0.54
     bibli
    0.52
     indústria
    0.52
     Empresas
    0.52
     Angaben
    0.52
    行业的
    0.50
     आयुक्त
    0.50
    POSITIVE LOGITS
     party
    1.62
    Party
    1.57
     Party
    1.55
    party
    1.54
     पार्टी
    1.50
     PARTY
    1.49
     پارٹی
    1.47
    黨
    1.47
     పార్టీ
    1.43
    党
    1.41
    Activations Density 0.134%

    No Known Activations