© 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. 191201
    Prev
    Next
    INDEX
    Explanations

    legacy class

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

    business, food, and specific entities

    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
     TouchUtils
    0.54
     サン
    0.53
     እንዲሁ
    0.53
     élevée
    0.52
     これは
    0.52
     συνε
    0.51
     Quatre
    0.51
     こう
    0.50
     ∀
    0.50
     カメラ
    0.49
    POSITIVE LOGITS
    Ancest
    0.54
    Punk
    0.49
    some
    0.47
    legacy
    0.47
    class
    0.46
    Legacy
    0.46
     legacy
    0.45
    rad
    0.45
    Well
    0.44
    Corps
    0.44
    Activations Density 0.001%

    No Known Activations