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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2548
    Prev
    Next
    INDEX
    Explanations

    tests and exams

    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_16_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
    יי
    0.50
    ა
    0.48
    י
    0.47
    кі
    0.47
    ਰ
    0.47
     winch
    0.46
    यों
    0.45
    עי
    0.45
    ీ
    0.45
     mallet
    0.44
    POSITIVE LOGITS
    ads
    0.44
    时间
    0.42
    时的
    0.42
     امتحان
    0.42
     tijd
    0.41
    信息
    0.41
    时
    0.40
     সম্মানিত
    0.40
    时间和
    0.40
    考试
    0.39
    Activations Density 0.134%

    No Known Activations