© 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. 9603
    Prev
    Next
    INDEX
    Explanations

    social welfare system exploitation

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

    The neuron activates on mentions of government social‐welfare or benefits agencies—especially references to “social security.”

    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
     Candy
    0.63
     Jody
    0.63
     পেঁয়
    0.63
    Candy
    0.60
    甜
    0.60
    deployed
    0.59
    deploy
    0.58
    Loire
    0.58
     फीस
    0.57
    บค
    0.57
    POSITIVE LOGITS
     claimants
    0.89
     disability
    0.88
     claimant
    0.88
     pension
    0.86
     Social
    0.85
     pensions
    0.84
     ጡ
    0.83
     SSA
    0.82
     पेंशन
    0.79
     pensioner
    0.77
    Activations Density 0.262%

    No Known Activations