© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    equation, Schiff, policy, door

    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
    Jackie
    0.37
    hus
    0.37
    lowest
    0.36
     week
    0.36
    СР
    0.34
     piggy
    0.34
    erry
    0.34
     cohorts
    0.34
    \}$
    0.34
     Lenn
    0.34
    POSITIVE LOGITS
     FileName
    0.47
     Equation
    0.46
     equation
    0.45
     Allgemeine
    0.45
    檔案
    0.45
    方程
    0.45
     фай
    0.44
     уравнение
    0.43
    Arquivo
    0.43
    Equation
    0.42
    Activations Density 0.000%

    No Known Activations