© 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. 41-GEMMASCOPE-2-RES-65K
    7. 14057
    Prev
    Next
    INDEX
    Explanations

    alcohol, drugs, substance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     heroin
    0.72
     marijuana
    0.62
    Pharmaceutical
    0.58
     Uranium
    0.57
    Drug
    0.56
    盘
    0.55
    Liqu
    0.55
    Casino
    0.55
    ダイヤモンド
    0.55
     methamphetamine
    0.55
    POSITIVE LOGITS
     abuse
    1.27
     misuse
    1.22
     Abuse
    1.17
     abuso
    1.05
    abuse
    1.04
     abused
    1.00
    滥
    0.93
     misused
    0.87
     दुरुपयोग
    0.87
     consumption
    0.87
    Activations Density 0.039%

    No Known Activations