© 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-65K
    7. 47627
    Prev
    Next
    INDEX
    Explanations

    social, logical, or conditional connectors

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nods
    0.44
    觎
    0.42
     nodding
    0.40
    गान
    0.40
    儿
    0.39
    শ্ত
    0.39
    iguë
    0.38
    氳
    0.38
    еро
    0.38
     طلبه
    0.38
    POSITIVE LOGITS
     تعداد
    0.41
    ეთი
    0.38
     Freedman
    0.38
    phabet
    0.38
     đoàn
    0.35
    APT
    0.35
    iatan
    0.35
     Letter
    0.35
    ataka
    0.35
     才
    0.34
    Activations Density 0.000%

    No Known Activations