© 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. 90470
    Prev
    Next
    INDEX
    Explanations

    compilation process

    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
     work
    0.55
     meet
    0.55
     탐
    0.55
     talk
    0.54
     Porque
    0.53
    ز
    0.52
     صلاحیت
    0.51
    。",
    0.50
     کار
    0.50
     paragraph
    0.50
    POSITIVE LOGITS
    3
    0.56
    5
    0.54
    4
    0.53
    fence
    0.52
    gages
    0.51
     nových
    0.50
     Inu
    0.50
     Filipinos
    0.49
    6
    0.49
    2
    0.49
    Activations Density 0.000%

    No Known Activations