© 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. 35807
    Prev
    Next
    INDEX
    Explanations

    legal arguments or Bitcoin

    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
    рів
    0.52
    血
    0.50
    添加到
    0.46
    我
    0.46
    오
    0.45
    如图
    0.45
     년
    0.44
    的時間
    0.43
    سط
    0.43
    بد
    0.43
    POSITIVE LOGITS
     },
    0.51
     laughed
    0.50
     웃
    0.48
    ्या
    0.47
     ।
    0.47
     उद्य
    0.46
     उक्त
    0.46
    s
    0.46
    ine
    0.46
     laughs
    0.46
    Activations Density 0.000%

    No Known Activations