© 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. 48646
    Prev
    Next
    INDEX
    Explanations

    identification number

    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
    シア
    0.43
    начала
    0.43
     পেরিয়ে
    0.43
     außergewöhn
    0.42
    ⚭
    0.42
     meninggal
    0.41
     murdered
    0.41
     Internation
    0.41
    beach
    0.41
     گاز
    0.41
    POSITIVE LOGITS
    ֵ
    0.52
    理解
    0.51
     \[
    0.50
     numpy
    0.48
     conceptually
    0.46
     [\
    0.46
    揖
    0.45
    各自
    0.45
     plotting
    0.45
     누
    0.45
    Activations Density 0.006%

    No Known Activations