© 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. 239848
    Prev
    Next
    INDEX
    Explanations

    coins and discounts

    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
    ristmas
    0.46
    朋友
    0.46
    計畫
    0.45
    க
    0.45
    睢
    0.45
    記載
    0.45
    ники
    0.44
     име
    0.44
    烩
    0.43
    qr
    0.43
    POSITIVE LOGITS
     شدہ
    0.50
     Teflon
    0.46
     tol
    0.46
     manifold
    0.45
    াঃ
    0.45
     ገን
    0.44
     탱크
    0.43
     পি
    0.43
     chast
    0.42
     tent
    0.42
    Activations Density 0.000%

    No Known Activations