© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220122
    Prev
    Next
    INDEX
    Explanations

    fundamental arithmetic, speak English, sophisticated joke

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ปัญหา
    0.42
    ☀
    0.42
    ージー
    0.41
    🦷
    0.41
     बुद्ध
    0.39
    зацию
    0.39
    तरंज
    0.39
     fárm
    0.38
    辻
    0.38
     scolded
    0.38
    POSITIVE LOGITS
    шов
    0.38
     خریداری
    0.37
    现
    0.37
    CONNE
    0.36
     الالكتروني
    0.36
     covers
    0.36
     широ
    0.35
    UED
    0.35
    max
    0.34
     transporters
    0.34
    Activations Density 0.000%

    No Known Activations