© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 203533
    Prev
    Next
    INDEX
    Explanations

    as defined below

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

    decrease or diminish

    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
    ↵↵
    0.46
    ्वे
    0.43
    的需求
    0.43
     Installing
    0.43
    菜
    0.42
    票
    0.42
    ार्म
    0.41
    =============
    0.41
    }\}$
    0.41
    的代码
    0.40
    POSITIVE LOGITS
     diminu
    0.58
     diminish
    0.53
     decrease
    0.52
     	
    0.51
     diminished
    0.51
     أص
    0.48
     diminuer
    0.48
     dismin
    0.48
     fó
    0.47
     decreased
    0.47
    Activations Density 0.002%

    No Known Activations