© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9436
    Prev
    Next
    INDEX
    Explanations

    reduces model size or blocks traffic

    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
    ین
    0.57
     sağlıklı
    0.55
    িকপ্ট
    0.49
     ऑर्गेनिक
    0.45
     벗
    0.44
     Inflation
    0.43
     Sản
    0.43
     مکتی
    0.43
     تولید
    0.43
    组成的
    0.42
    POSITIVE LOGITS
     visitor
    0.51
     sat
    0.48
    5
    0.47
     Master
    0.47
    a
    0.46
     head
    0.45
     connection
    0.45
     master
    0.44
     movie
    0.44
    6
    0.44
    Activations Density 0.008%

    No Known Activations