© 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. 31-GEMMASCOPE-2-RES-262K
    7. 153370
    Prev
    Next
    INDEX
    Explanations

    tied theand shalldogs 1sadness withto !don cosy1 4breakers canof loud

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

    democracy and damage

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ляет
    0.47
    asına
    0.47
     पद्धतीने
    0.47
     লন্ড
    0.45
     আর্মি
    0.44
    扆
    0.44
     ইসলামাবাদের
    0.43
    átil
    0.43
     কমান্ডার
    0.43
    পাকিস্তানের
    0.43
    POSITIVE LOGITS
    「
    0.43
     dehuman
    0.42
     imperfection
    0.41
     recipro
    0.40
     reduction
    0.39
    _"+
    0.39
     imp
    0.39
    羨
    0.38
    是非
    0.38
     redu
    0.38
    Activations Density 0.000%

    No Known Activations