© 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. 31-GEMMASCOPE-2-RES-262K
    7. 200225
    Prev
    Next
    INDEX
    Explanations

    system messages and instructions

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ม
    0.62
    มัน
    0.58
    ים
    0.51
    Poppins
    0.49
     રંગ
    0.48
    Montserrat
    0.48
    shark
    0.47
    VENTORY
    0.47
    ก
    0.47
    م
    0.46
    POSITIVE LOGITS
     koop
    0.46
     molded
    0.46
     cudd
    0.45
     tendons
    0.45
     ovens
    0.44
     franchisees
    0.43
     filth
    0.43
     preg
    0.42
     nakk
    0.42
     nast
    0.42
    Activations Density 0.001%

    No Known Activations