© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    swirling vortex

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    zul
    1.30
    ️
    1.28
    ✨
    1.25
     DeFi
    1.24
     👀
    1.21
    🤝
    1.20
     YouTuber
    1.19
    ️⃣
    1.19
     Thr
    1.19
     Villain
    1.18
    POSITIVE LOGITS
     doubtless
    1.24
     quite
    1.23
     tunic
    1.19
     camisa
    1.18
    烟
    1.17
     probably
    1.16
     evidently
    1.15
     cip
    1.10
     hoped
    1.10
     поги
    1.10
    Activations Density 0.091%

    No Known Activations