© 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. 10124
    Prev
    Next
    INDEX
    Explanations

    law enforcement and military contexts

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

    The neuron fires on mentions of police or law‐enforcement 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
    ಿಕ
    0.66
     Đảng
    0.60
     Hải
    0.58
     передачи
    0.57
     अधीनस्थों
    0.57
     Indicators
    0.55
    }");
    0.55
     Polri
    0.55
    }\}$.
    0.55
     ‏
    0.54
    POSITIVE LOGITS
    స్ట
    0.73
    कर्मियों
    0.64
    wort
    0.62
    Presence
    0.61
    上記の
    0.61
    リューム
    0.61
    presence
    0.60
    hort
    0.59
    บร
    0.59
    ವರಿ
    0.59
    Activations Density 0.112%

    No Known Activations