© 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-16K
    7. 311
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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_16k_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
     disjoint
    0.26
     ব্যবহার
    0.25
    参数
    0.24
     quantité
    0.23
     Siamese
    0.23
    鸴
    0.23
     Bayesian
    0.22
    关节
    0.22
     Grandmother
    0.22
    変数
    0.22
    POSITIVE LOGITS
     tahun
    0.30
     dicembre
    0.29
     letech
    0.28
     latach
    0.28
     năm
    0.27
    년
    0.25
     mwaka
    0.25
     yıll
    0.24
     década
    0.24
     años
    0.24
    Activations Density 0.164%

    No Known Activations