© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

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

    witchcraft, drip, classical, Veteran, Fol, linguistic

    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
    Negative Logits
    莉
    0.42
     дочь
    0.35
     היא
    0.35
    ísica
    0.35
    ית
    0.35
     дочери
    0.35
    ญิง
    0.34
    щая
    0.34
     딸
    0.34
     소녀
    0.34
    POSITIVE LOGITS
     concurrent
    0.31
     slower
    0.29
     civilian
    0.28
     benchmarks
    0.28
     smaller
    0.28
     John
    0.26
     endpoints
    0.26
     unarmed
    0.25
     run
    0.25
     Paul
    0.25
    Activations Density 1.738%

    No Known Activations