© 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. 235385
    Prev
    Next
    INDEX
    Explanations

    when you do something

    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
    茴
    0.43
    蹼
    0.42
     sắt
    0.41
    ราะห์
    0.41
    越来越多
    0.40
     Москве
    0.40
     afternoons
    0.40
    ጥነት
    0.40
    డే
    0.40
     Bí
    0.40
    POSITIVE LOGITS
    kah
    0.44
    ˌ
    0.42
    urun
    0.40
    even
    0.40
    never
    0.40
    plugin
    0.39
    ko
    0.39
    extract
    0.39
     vetted
    0.38
    config
    0.38
    Activations Density 0.001%

    No Known Activations