© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1615
    Prev
    Next
    INDEX
    Explanations

    making meth, DMT, or lsd

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Widgets
    0.51
    әне
    0.47
    Widgets
    0.47
     комі
    0.47
     LinkedList
    0.46
     фон
    0.45
    Constraint
    0.42
     Widget
    0.42
    愤
    0.41
     Wireless
    0.41
    POSITIVE LOGITS
     cannabis
    1.81
     marijuana
    1.63
     Cannabis
    1.58
     cannabinoids
    1.49
     cannabin
    1.47
     THC
    1.45
     psychedelic
    1.43
     Marijuana
    1.43
     marihuana
    1.36
     sativa
    1.23
    Activations Density 0.210%

    No Known Activations