© 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. 36884
    Prev
    Next
    INDEX
    Explanations

    impressive performance, become less

    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
    ா
    0.46
    军队
    0.40
    蓥
    0.40
     شيء
    0.39
    .</
    0.39
    În
    0.38
    住房
    0.38
    Ĩ
    0.37
    竑
    0.37
    Database
    0.37
    POSITIVE LOGITS
     smells
    0.56
     smelling
    0.54
     sintomas
    0.52
    gluten
    0.50
     aroma
    0.50
     chirp
    0.50
     correlations
    0.48
     ukuran
    0.48
     certeza
    0.48
     thơm
    0.48
    Activations Density 0.009%

    No Known Activations