© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8528
    Prev
    Next
    INDEX
    Explanations

    bioactive compounds and drugs

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

    phytochemicals and compounds

    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_40_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
     लिमिट
    0.45
     आवेग
    0.43
     Uranium
    0.43
     Fibre
    0.42
    纤维
    0.42
     ಕಬ್ಬಿಣ
    0.41
    铊
    0.41
    coal
    0.40
    烝
    0.40
    ශ්
    0.40
    POSITIVE LOGITS
     phytochemical
    0.95
     compounds
    0.89
    化合物
    0.87
     bioactive
    0.84
     compound
    0.82
     Compounds
    0.80
     screening
    0.77
    Compounds
    0.77
     flavonoids
    0.76
     pharmacological
    0.76
    Activations Density 0.264%

    No Known Activations