© 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. 91239
    Prev
    Next
    INDEX
    Explanations

    institutional entities and terms

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

    during WWII

    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
    मु
    0.49
     enzyme
    0.48
     colle
    0.47
    นอก
    0.46
     ಹೇಳ
    0.45
    ม
    0.44
    ਪ
    0.44
    เรา
    0.44
     analyst
    0.43
    դ
    0.43
    POSITIVE LOGITS
     Bishops
    0.50
    aparikkh
    0.48
     Governors
    0.46
     Instruction
    0.46
    ೫
    0.45
     Dull
    0.45
     ஊராட்சி
    0.44
     Schema
    0.43
     Soviets
    0.43
    ändige
    0.43
    Activations Density 0.001%

    No Known Activations