© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3482
    Prev
    Next
    INDEX
    Explanations

    Product names and model numbers

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

    modelmodel versions and numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     संघटना
    0.32
    lardır
    0.31
     मंत्राल
    0.30
    财政
    0.30
    والفق
    0.30
    呃
    0.29
     subordination
    0.29
    欤
    0.29
     ફરિયા
    0.29
     えっ
    0.29
    POSITIVE LOGITS
    0.38
     titanium
    0.32
     II
    0.30
     Edition
    0.30
     I
    0.30
     edition
    0.30
     capsule
    0.29
     M
    0.29
     +
    0.29
     polypropylene
    0.28
    Activations Density 0.477%

    No Known Activations