© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4668
    Prev
    Next
    INDEX
    Explanations

    tests and testing

    np_acts-logits-general · gemini-2.5-flash-lite

    hypothesis testing

    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
     DENUMIRE
    0.36
    SdkError
    0.35
     சொ
    0.34
    十八章
    0.33
    miyor
    0.32
     ফো
    0.32
     szeptember
    0.32
    䅐
    0.31
     Tully
    0.30
     בעי
    0.30
    POSITIVE LOGITS
     test
    4.75
    测试
    4.72
    測試
    4.56
    テスト
    4.50
     테스트
    4.47
     testing
    4.38
     tests
    4.34
     Test
    4.16
     测试
    4.16
     testen
    4.13
    Activations Density 0.499%

    No Known Activations