© 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. 173944
    Prev
    Next
    INDEX
    Explanations

    create bus technology County until abilities

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

    flower and branch combinations

    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
     RPS
    0.52
    侷
    0.46
     logró
    0.45
     確認
    0.45
     persön
    0.44
     ಸ್ವ
    0.44
    IMAGES
    0.44
    listView
    0.42
    人數
    0.42
     ಶ್ರೀ
    0.42
    POSITIVE LOGITS
    aisu
    0.46
     loopholes
    0.46
    τυ
    0.45
    හෙ
    0.44
    谀
    0.44
    жами
    0.43
    馨
    0.43
    ataka
    0.42
     উপলক্ষে
    0.41
    τία
    0.41
    Activations Density 0.006%

    No Known Activations