© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1348
    Prev
    Next
    INDEX
    Explanations

    policy makers and lawmakers

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

    The neuron activates on names of organizations, institutions, or stakeholder groups (e.g. clinicians, administrators, policy makers, the European Union).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    });*/
    -0.97
    ...»
    -0.90
    ㅓ
    -0.90
    NNN
    -0.88
     salari
    -0.88
    ברית
    -0.88
    seal
    -0.86
     sonda
    -0.86
     Firma
    -0.86
    suits
    -0.86
    POSITIVE LOGITS
     policymakers
    4.28
     policy
    3.22
     politicians
    2.88
     decision
    2.59
     lawmakers
    2.59
     governments
    2.48
    policy
    2.39
     authorities
    2.36
     legislators
    2.34
    Policy
    2.28
    Activations Density 0.111%

    No Known Activations