© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137704
    Prev
    Next
    INDEX
    Explanations

    describing states or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    MRT
    0.41
    BMP
    0.40
     INVESTMENT
    0.40
    未
    0.38
    ritis
    0.37
    INOIS
    0.37
     المج
    0.37
    饼
    0.36
    द्वीप
    0.36
     legis
    0.36
    POSITIVE LOGITS
     થયું
    0.46
    اکی
    0.41
    คาเด
    0.41
    equipped
    0.40
     주인
    0.40
    umba
    0.40
    chad
    0.39
     fizemos
    0.39
    ふわ
    0.39
    équip
    0.38
    Activations Density 0.001%

    No Known Activations