© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 459
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ساعدة
    1.49
     کردن
    1.37
     では
    1.32
    例外
    1.24
     نکن
    1.21
    階段
    1.21
    遜
    1.20
    你會
    1.17
    你会
    1.15
     اقول
    1.15
    POSITIVE LOGITS
     handled
    2.19
     taken
    2.18
     executed
    2.15
     conveyed
    2.13
     transferred
    2.11
     eaten
    2.10
     delivered
    2.07
     examined
    2.03
     relayed
    2.03
     procured
    2.01
    Activations Density 4.708%

    No Known Activations