© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13027
    Prev
    Next
    INDEX
    Explanations

    testing if something works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    ו
    0.70
    リ
    0.60
     forcible
    0.59
    ни
    0.58
    </u>
    0.57
    </h2>
    0.57
    ва
    0.57
    ுடன்
    0.57
    و
    0.57
     vingt
    0.56
    POSITIVE LOGITS
    Testing
    1.41
    测试
    1.41
     Testing
    1.34
     testing
    1.32
     test
    1.31
    Test
    1.31
     测试
    1.30
     테스트
    1.29
     اختبار
    1.26
    測試
    1.25
    Activations Density 0.071%

    No Known Activations