© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 500
    Prev
    Next
    INDEX
    Explanations

    Endowment for

    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_53_width_65k_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
    ของการ
    0.30
     பதில
    0.28
    +}^{
    0.27
    りの
    0.27
    btnUn
    0.27
    בה
    0.27
    ﻌ
    0.27
    靘
    0.26
    筞
    0.26
     stk
    0.26
    POSITIVE LOGITS
     ot
    0.31
     [&
    0.30
    iew
    0.30
     fo
    0.28
    wes
    0.28
    انا
    0.28
    ców
    0.27
     Fo
    0.27
    ictures
    0.27
    ड़ियों
    0.27
    Activations Density 0.789%

    No Known Activations