© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44678
    Prev
    Next
    INDEX
    Explanations

    consequences and instructions

    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
    Negative Logits
    ۵
    0.51
    え
    0.47
    ین
    0.43
    6
    0.43
    ن
    0.42
    ۴
    0.41
    น
    0.41
    éraire
    0.41
    ਵ
    0.41
    一条
    0.40
    POSITIVE LOGITS
     gacchati
    0.46
     sorgt
    0.45
     hidup
    0.45
     Vertrags
    0.44
     gewährleisten
    0.44
     NFS
    0.44
     instruções
    0.44
     suport
    0.43
    bibfield
    0.43
    ́i
    0.43
    Activations Density 0.012%

    No Known Activations