© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8672
    Prev
    Next
    INDEX
    Explanations

    online pharmacies selling drugs

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

    pharmacy, pharmacist, pharmaceutical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    粼
    0.43
    亽
    0.42
    颀
    0.41
    伥
    0.40
     ভোক
    0.40
    鹅
    0.40
    🦑
    0.38
    侣
    0.38
    教练
    0.38
    筍
    0.38
    POSITIVE LOGITS
     pharmacy
    3.92
     Pharmacy
    3.72
    Pharmacy
    3.64
     Pharmac
    3.59
     pharmacists
    3.58
     pharmacist
    3.56
     pharmacies
    3.56
     pharmac
    3.53
    pharm
    3.52
     pharmaceutical
    3.50
    Activations Density 0.149%

    No Known Activations