© 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-262K
    7. 253135
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lawful
    0.44
     estates
    0.40
     bâtiments
    0.39
    SaveChangesAsync
    0.39
     중심
    0.39
     foundations
    0.38
    vação
    0.38
    Ტ
    0.38
     обов
    0.38
     strength
    0.38
    POSITIVE LOGITS
     Sport
    0.51
     स्पोर्ट
    0.50
     Experience
    0.50
     Ready
    0.47
     femelle
    0.47
     Erfahrung
    0.47
    nu
    0.46
     ọ
    0.46
     Asian
    0.45
    tec
    0.45
    Activations Density 0.002%

    No Known Activations