© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8843
    Prev
    Next
    INDEX
    Explanations

    discarding surplus items

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

    waste, leftovers, discarded items

    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_40_width_16k_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
     महासचिव
    0.40
     اتح
    0.39
     compound
    0.37
     وقل
    0.36
     compounded
    0.35
     زنج
    0.35
    폄
    0.35
     critical
    0.35
    밭
    0.34
     applied
    0.34
    POSITIVE LOGITS
     discarded
    1.63
     leftover
    1.62
     leftovers
    1.55
     surplus
    1.49
     unused
    1.43
    discard
    1.36
    unused
    1.32
     Surplus
    1.31
    废
    1.30
     surpluses
    1.25
    Activations Density 0.476%

    No Known Activations