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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33062
    Prev
    Next
    INDEX
    Explanations

    decrease, decline, drop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (++
    -1.09
    ++)
    -1.02
    ++
    -0.94
    [++
    -0.92
    ++
    -0.92
    lceil
    -0.92
    ++.
    -0.90
    больше
    -0.88
    加速
    -0.88
    Upgradeable
    -0.87
    POSITIVE LOGITS
     decline
    4.06
     decrease
    3.50
     declines
    3.39
     declining
    3.33
     declined
    3.33
     Decline
    3.11
     decreases
    3.02
     decreased
    3.00
     drop
    3.00
     decreasing
    2.91
    Activations Density 0.162%

    No Known Activations