© 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. 16-GEMMASCOPE-2-RES-262K
    7. 107287
    Prev
    Next
    INDEX
    Explanations

    grenada, cosmopolitan, margaritas

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Technology
    0.52
    왈
    0.51
    וק
    0.50
    Platforms
    0.49
    tiden
    0.47
    Frontend
    0.47
    tekn
    0.46
    ूज
    0.46
    front
    0.46
     Platforms
    0.46
    POSITIVE LOGITS
     नींद
    0.48
     که
    0.48
    Џ
    0.47
     transcribed
    0.47
     بین
    0.47
     را
    0.46
     puzzling
    0.45
     ނ
    0.45
     mesmo
    0.45
     comprising
    0.44
    Activations Density 0.000%

    No Known Activations