© 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. 35666
    Prev
    Next
    INDEX
    Explanations

    dodging attacks and responsibility

    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
     =
    0.58
    تمد
    0.52
     language
    0.52
    tic
    0.48
     igény
    0.48
     אי
    0.47
    eq
    0.47
    INE
    0.46
     Tic
    0.46
    Buddy
    0.46
    POSITIVE LOGITS
    с
    0.63
    вак
    0.62
    ја
    0.61
    мак
    0.60
    ъ
    0.60
    рак
    0.57
     dodging
    0.57
    
    0.57
    ä
    0.57
    дак
    0.57
    Activations Density 0.025%

    No Known Activations