© 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. 26891
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
     многи
    0.46
     использует
    0.46
    Х
    0.45
     대학
    0.43
    Questo
    0.43
    Otros
    0.43
    󰡔
    0.43
     הס
    0.43
    Otro
    0.42
     Хотя
    0.41
    POSITIVE LOGITS
     remember
    0.55
     Remember
    0.52
     Before
    0.50
     quando
    0.49
     beforeEach
    0.48
     BEFORE
    0.48
     When
    0.47
    remember
    0.47
     প্রথমে
    0.46
     Quando
    0.46
    Activations Density 0.016%

    No Known Activations