© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20651
    Prev
    Next
    INDEX
    Explanations

    creating data for testing

    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
     తెలియ
    0.43
     గ
    0.40
     directive
    0.38
     जाणून
    0.38
     hint
    0.38
    angkutan
    0.37
     ګ
    0.37
    懾
    0.37
     intelligently
    0.37
    अर्
    0.37
    POSITIVE LOGITS
     testing
    0.73
     Testing
    0.62
    Testing
    0.61
    testing
    0.59
     testen
    0.57
    测试
    0.57
     테스트
    0.56
     test
    0.55
     study
    0.55
    样本
    0.52
    Activations Density 0.248%

    No Known Activations