© 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. 47374
    Prev
    Next
    INDEX
    Explanations

    Champ de Mars; champagne

    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
    ่ะ
    0.49
    sframe
    0.41
     столб
    0.40
    WriteHeader
    0.40
     นึง
    0.39
     массы
    0.39
    考えると
    0.39
    희
    0.38
    reathe
    0.38
     જી
    0.38
    POSITIVE LOGITS
     named
    0.43
     choice
    0.43
     pilihan
    0.40
    BIS
    0.40
    Choice
    0.39
    خانه
    0.39
     escol
    0.39
    מיד
    0.39
     nommé
    0.38
    μη
    0.38
    Activations Density 0.002%

    No Known Activations