© 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. 23879
    Prev
    Next
    INDEX
    Explanations

    records, objects, folders, and declarations

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

    technical computing terms

    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
    宮
    0.42
     থাকিতে
    0.41
    କୁ
    0.40
     অথবা
    0.40
     ロング
    0.39
     東
    0.38
    ତି
    0.38
     宮
    0.38
     Mortgage
    0.37
     whale
    0.37
    POSITIVE LOGITS
    acteur
    0.42
     заявил
    0.41
     எதிர்ப்பு
    0.41
    への
    0.41
    群众
    0.41
    xiety
    0.40
     komplett
    0.40
     erscheinen
    0.40
     countenance
    0.40
     entsprechenden
    0.39
    Activations Density 0.000%

    No Known Activations