© 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. 56369
    Prev
    Next
    INDEX
    Explanations

    National programs, initiatives, or entities

    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
    外国
    0.46
     držav
    0.44
     Kementerian
    0.43
    国際
    0.43
     சர்வதேச
    0.43
    頔
    0.42
     national
    0.41
     націона
    0.41
    international
    0.40
    ementerian
    0.40
    POSITIVE LOGITS
    FLE
    0.39
     curs
    0.39
     واس
    0.39
     +,
    0.38
     assembly
    0.37
    ,,
    0.37
    MG
    0.37
    Brands
    0.37
    ,:
    0.36
     टार
    0.36
    Activations Density 0.004%

    No Known Activations