© 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-65K
    7. 47611
    Prev
    Next
    INDEX
    Explanations

    Self, Initial, minimize

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Chávez
    0.45
     execut
    0.41
    隨
    0.40
     gener
    0.38
     públic
    0.38
     integ
    0.38
     período
    0.37
     gê
    0.36
     Zuckerberg
    0.36
     affront
    0.36
    POSITIVE LOGITS
    Maps
    0.47
    Bills
    0.47
     समायोजित
    0.42
     ㅏ
    0.41
    Versions
    0.41
    Mind
    0.40
     habits
    0.38
    Adjust
    0.38
    IPT
    0.38
     چې
    0.38
    Activations Density 0.005%

    No Known Activations