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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69670
    Prev
    Next
    INDEX
    Explanations

    ecommerce contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ەی
    2.05
    썸
    2.00
    お金
    1.98
     económ
    1.93
    èques
    1.93
    กัด
    1.92
     anggaran
    1.90
    不愿意
    1.90
     szeret
    1.89
     económicos
    1.88
    POSITIVE LOGITS
    Conclusion
    1.10
     restart
    1.05
    indruck
    1.04
     minded
    1.01
    CONCLUSION
    0.98
     Conclusion
    0.95
    ❱
    0.94
     deci
    0.93
     nirv
    0.93
    徒
    0.90
    Activations Density 0.005%

    No Known Activations