© 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-65K
    7. 44847
    Prev
    Next
    INDEX
    Explanations

    financial, economic, legal, physical, nationality, vehicle, simple

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    在
    0.49
    6
    0.46
    2
    0.46
    mathrm
    0.45
    3
    0.45
     in
    0.44
    Ε
    0.44
     utilized
    0.43
    ρέ
    0.43
     utilizzare
    0.43
    POSITIVE LOGITS
    intahan
    0.53
     stuffs
    0.52
     materialistic
    0.50
     equipments
    0.50
     sufferings
    0.49
    💹
    0.45
     htim
    0.44
     shayari
    0.43
     squre
    0.43
     scanty
    0.43
    Activations Density 0.032%

    No Known Activations