© 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. 122516
    Prev
    Next
    INDEX
    Explanations

    foreclosure auction, Term Glossary, local movements

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

    assurance, verification, understanding

    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
    україн
    0.52
    歐
    0.50
    欧盟
    0.46
    喝
    0.45
     clotting
    0.45
     可能
    0.44
     吸
    0.43
     短
    0.43
     Ново
    0.43
     drink
    0.42
    POSITIVE LOGITS
     visualizar
    0.52
    baş
    0.51
     between
    0.48
    𝚊
    0.48
    uć
    0.47
     iti
    0.47
    inin
    0.46
     unambiguously
    0.46
    ਪ
    0.46
    between
    0.46
    Activations Density 0.000%

    No Known Activations