© 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. 40-GEMMASCOPE-2-RES-262K
    7. 24766
    Prev
    Next
    INDEX
    Explanations

    building numbers

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    回头
    0.40
    リル
    0.39
    迷惑
    0.39
    ên
    0.39
     nécessairement
    0.38
     것
    0.37
    锐
    0.37
    便是
    0.37
    便
    0.37
     Où
    0.37
    POSITIVE LOGITS
     sowohl
    0.46
    ^*(
    0.45
    ꧁
    0.44
     தொழில்நுட்ப
    0.43
     ​​​​
    0.42
    𒆠
    0.41
     XNUMX
    0.41
    نوع
    0.41
     খুবই
    0.41
    াক্তন
    0.41
    Activations Density 0.000%

    No Known Activations