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

    Neuronpedia

    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. 39830
    Prev
    Next
    INDEX
    Explanations

    first release versions

    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
    これらの
    0.52
    标
    0.49
    这些
    0.46
     これらの
    0.45
     这些
    0.45
    SwingConstants
    0.44
    ปี
    0.42
    標
    0.42
     resiliency
    0.42
    ファイルを
    0.42
    POSITIVE LOGITS
     første
    0.53
     första
    0.52
     pertama
    0.52
     Pertama
    0.49
     initial
    0.48
    erste
    0.48
    czenie
    0.47
     makanan
    0.47
     enquiries
    0.47
     eerste
    0.46
    Activations Density 0.021%

    No Known Activations