© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7101
    Prev
    Next
    INDEX
    Explanations

    reports pain and symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    írez
    1.19
    呪
    1.17
     gayi
    1.13
    Miami
    1.10
     сердце
    1.08
    Fury
    1.07
     сути
    1.07
     получится
    1.05
     сю
    1.05
     водой
    1.05
    POSITIVE LOGITS
     的
    1.34
     이러한
    1.32
     一个
    1.27
     সাধারণত
    1.24
     用于
    1.23
    很多的
    1.20
     frequently
    1.18
     使用
    1.18
     या
    1.17
     为了
    1.17
    Activations Density 0.174%

    No Known Activations