© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11217
    Prev
    Next
    INDEX
    Explanations

    hormone secretion and chemical compounds

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

    vitamin D deficiency ketamine use

    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
     nutrients
    0.46
     vitamins
    0.46
    ेश्वरी
    0.46
     puna
    0.45
    फील्ड
    0.44
    价
    0.44
     hormones
    0.43
    readystate
    0.43
    bourne
    0.42
     phenytoin
    0.42
    POSITIVE LOGITS
     synthase
    0.49
     HCl
    0.48
    HCl
    0.45
     $(*
    0.43
     hydrochloride
    0.43
    -(
    0.43
     bonded
    0.43
     (<
    0.42
     mediated
    0.42
     derivative
    0.42
    Activations Density 0.234%

    No Known Activations