© 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. 226876
    Prev
    Next
    INDEX
    Explanations

    acting, transparent, Kubernetes, European union

    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
     polymers
    0.46
    抧
    0.46
     yachts
    0.46
    تهم
    0.45
    మ్‌
    0.44
     ТО
    0.44
     해서
    0.43
    IW
    0.43
    Hfn
    0.43
    মোহন
    0.43
    POSITIVE LOGITS
     mancanza
    0.49
     tuttavia
    0.47
     проблемой
    0.47
     understated
    0.46
     problemi
    0.45
     %
    0.44
    囹
    0.43
     Oren
    0.43
     azonban
    0.43
    пред
    0.42
    Activations Density 0.000%

    No Known Activations