© 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. 41-GEMMASCOPE-2-RES-262K
    7. 103562
    Prev
    Next
    INDEX
    Explanations

    Kimberly Davies

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    钕
    0.46
    OE
    0.39
    ionine
    0.39
    ူ
    0.39
    蛛
    0.38
    ผลิตภัณฑ์
    0.37
    िवार
    0.36
    的产品
    0.36
     }_{
    0.36
    truck
    0.36
    POSITIVE LOGITS
     balconies
    0.42
     creature
    0.41
     pour
    0.41
     Village
    0.40
     kiss
    0.40
     Tuscany
    0.40
    rous
    0.40
     plaques
    0.40
     om
    0.39
    uste
    0.39
    Activations Density 0.000%

    No Known Activations