© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171954
    Prev
    Next
    INDEX
    Explanations

    inquiries

    np_acts-logits-general · gemini-2.5-flash-lite

    image segmentation or regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Lex
    0.50
    小朋友
    0.48
    说明
    0.48
    詈
    0.46
    Rating
    0.45
    Provider
    0.45
     Provider
    0.44
     Netflix
    0.44
    K
    0.44
    S
    0.44
    POSITIVE LOGITS
    
    0.55
     моно
    0.54
     اید
    0.53
    𝟰
    0.51
     εν
    0.51
     моделей
    0.51
     monof
    0.50
     wyłącznie
    0.50
     adept
    0.50
     έγ
    0.50
    Activations Density 0.010%

    No Known Activations